© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 5440
    Prev
    Next
    INDEX
    Explanations

    rel

    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
    ewolf
    -0.08
    涣
    -0.07
    grily
    -0.07
    🥤
    -0.07
    พยาย
    -0.07
     ServletException
    -0.07
     persu
    -0.07
     plethora
    -0.07
    .dds
    -0.07
    늦
    -0.07
    POSITIVE LOGITS
     Mini
    0.08
    (accounts
    0.07
     exhibits
    0.07
     establishments
    0.07
     basin
    0.07
    (input
    0.07
    엗
    0.06
     casa
    0.06
    וקר
    0.06
     QDir
    0.06
    Activations Density 0.288%

    No Known Activations