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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61896
    Prev
    Next
    INDEX
    Explanations

    ThinkPHP ThinkThinkFormSettingsgrepPostedDepartment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃ©
    -0.10
    acia
    -0.10
    ello
    -0.09
    ely
    -0.09
    ним
    -0.09
    icide
    -0.09
    ship
    -0.08
    conn
    -0.08
    ä¸įç»ıæĦı
    -0.08
    ider
    -0.08
    POSITIVE LOGITS
    cff
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.09
    请æĤ¨
    0.09
    ãģĵãģ¨ãģ§ãģĻ
    0.09
    ameleon
    0.09
    íĦ¸
    0.09
    ï¬Ħ
    0.09
    unist
    0.09
    ensity
    0.09
    åģ¶å°Ķ
    0.08
    Activations Density 0.080%

    No Known Activations