© 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. 75907
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    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
    ΰ
    -0.07
     assessment
    -0.07
    抛
    -0.07
    酬
    -0.07
    気に
    -0.07
    凭
    -0.07
     sais
    -0.07
     overtime
    -0.07
    依旧
    -0.06
    堪
    -0.06
    POSITIVE LOGITS
    :C
    0.08
    	J
    0.07
     prova
    0.07
    ervals
    0.07
    われ
    0.07
    יעה
    0.06
    _RTC
    0.06
     rooting
    0.06
    (now
    0.06
    Propagation
    0.06
    Activations Density 0.018%

    No Known Activations