Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 7275
    Prev
    Next
    INDEX
    Explanations

    technical and scientific articles

    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
    땜
    -0.07
    wf
    -0.06
    BREAK
    -0.06
     addCriterion
    -0.06
    ביטח
    -0.06
     pdo
    -0.06
    .getSharedPreferences
    -0.06
    ()]↵
    -0.06
    성이
    -0.06
     MEDIATEK
    -0.06
    POSITIVE LOGITS
    -sub
    0.08
    chedules
    0.07
     �
    0.07
     Đăng
    0.07
    晶体
    0.07
    -menu
    0.07
    菪
    0.07
    Occurrences
    0.06
    ucson
    0.06
    �
    0.06
    Activations Density 0.078%

    No Known Activations