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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2445
    Prev
    Next
    INDEX
    Explanations

    nn

    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
    .fecha
    -0.07
    第八
    -0.07
    닝
    -0.07
     행
    -0.07
    边
    -0.07
     propel
    -0.07
     девуш
    -0.07
    的过程中
    -0.07
    .Virtual
    -0.07
     에
    -0.06
    POSITIVE LOGITS
    丈
    0.07
     }↵
    0.07
    Downloads
    0.07
    ________________________________________________________________
    0.06
     различ
    0.06
    յ
    0.06
    Save
    0.06
     useStyles
    0.06
    통신
    0.06
     oui
    0.06
    Activations Density 0.000%

    No Known Activations