© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 21381
    Prev
    Next
    INDEX
    Explanations

    medicine and healthcare

    np_max-act · gemini-2.0-flash

    Technical biomedical or clinical content (scientific/medical terminology and discussions of diagnosis, treatment, or biological processes).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الأربعاء
    -0.07
     rồi
    -0.07
     пери
    -0.07
    .DATA
    -0.07
    אולי
    -0.07
    횽
    -0.06
    뇬
    -0.06
     Sexo
    -0.06
    oxid
    -0.06
    בטא
    -0.06
    POSITIVE LOGITS
    .force
    0.09
    .Direct
    0.07
     altered
    0.07
    bad
    0.07
    גלגל
    0.07
    альная
    0.07
    тельный
    0.07
    Won
    0.07
     ridiculously
    0.06
    勿
    0.06
    Activations Density 2.496%

    No Known Activations