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

    Neuronpedia

    APICircuit 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. 130862
    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
    -U
    -0.08
    Quick
    -0.07
     appe
    -0.07
    ovic
    -0.07
     sóc
    -0.07
     Jac
    -0.07
     MacDonald
    -0.07
    (an
    -0.07
    明确
    -0.07
    门户
    -0.06
    POSITIVE LOGITS
    安县
    0.06
     Revision
    0.06
    霪
    0.06
     HeaderComponent
    0.06
    FileDialog
    0.06
     Tier
    0.06
    特长
    0.06
     해결
    0.06
    来进行
    0.06
    本公司
    0.06
    Activations Density 0.000%

    No Known Activations