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. 130894
    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
    BOSE
    -0.08
     وهذه
    -0.07
    Ț
    -0.07
     nelle
    -0.07
     çek
    -0.07
     tenía
    -0.07
     alunos
    -0.07
    quí
    -0.07
     있어
    -0.07
     Então
    -0.07
    POSITIVE LOGITS
    ()
    ↵
    0.08
     upsetting
    0.08
     }.
    0.07
    读者
    0.07
    .Handled
    0.07
     Javascript
    0.07
     dashed
    0.07
    .parameter
    0.06
     rounding
    0.06
     (.
    0.06
    Activations Density 0.000%

    No Known Activations