© 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. 5086
    Prev
    Next
    INDEX
    Explanations

    local government elections

    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
    åħ¬åı¸ç«łç¨ĭ
    -0.09
    avad
    -0.09
    交æĺĵ
    -0.09
    ç½½
    -0.09
    ziehung
    -0.09
    à¸ķรà¸ĩ
    -0.08
    侮辱
    -0.08
    _ER
    -0.08
     ÑģÑĥд
    -0.08
    elsing
    -0.08
    POSITIVE LOGITS
    gMaps
    0.10
    æĻºæħ§åŁİå¸Ĥ
    0.09
    å®ĺåijĺ
    0.09
    еÑģÑĤи
    0.09
     officials
    0.08
    Ứ
    0.08
    ",-
    0.08
    ТЬ
    0.08
     horny
    0.08
     eminent
    0.08
    Activations Density 0.119%

    No Known Activations