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. 129662
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    fits
    -0.07
    /tr
    -0.07
     Cow
    -0.07
    /control
    -0.06
    рож
    -0.06
    므로
    -0.06
    ]))
    ↵
    -0.06
    -points
    -0.06
     Beatles
    -0.06
    等活动
    -0.06
    POSITIVE LOGITS
    折叠
    0.07
     obstruction
    0.07
     актив
    0.07
     labeling
    0.07
    _encoder
    0.07
     predict
    0.06
     prophet
    0.06
     skins
    0.06
     obstruct
    0.06
    渑
    0.06
    Activations Density 0.041%

    No Known Activations