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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 23529
    Prev
    Next
    INDEX
    Explanations

    gh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじ
    -0.08
    antas
    -0.07
    []↵
    -0.07
    尖叫
    -0.07
    참
    -0.07
    是最
    -0.07
    ää
    -0.07
     deber
    -0.07
    ään
    -0.07
    .trailing
    -0.07
    POSITIVE LOGITS
     Państwo
    0.07
    (Product
    0.07
    WHERE
    0.07
    :^{↵
    0.07
    خارج
    0.07
     pharmacy
    0.07
    פורט
    0.07
    .endDate
    0.07
     Do
    0.07
     LANGUAGE
    0.07
    Activations Density 0.027%

    No Known Activations