© 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. 19-RESID-POST-AA
    11. 89376
    Prev
    Next
    INDEX
    Explanations

    medical monitoring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wound
    -0.08
    ((((
    -0.08
    UserId
    -0.07
    完了
    -0.07
    用自己的
    -0.07
    标语
    -0.07
    カン
    -0.07
    琢
    -0.06
    一直都是
    -0.06
    小学
    -0.06
    POSITIVE LOGITS
     הש
    0.09
     יה
    0.07
     HP
    0.07
     đèn
    0.07
     substantially
    0.07
    쟎
    0.07
    Dog
    0.07
     Lots
    0.07
     experimenting
    0.06
     merits
    0.06
    Activations Density 0.069%

    No Known Activations