© 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. 54144
    Prev
    Next
    INDEX
    Explanations

    Partners Group

    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
    æѦè£ħ
    -0.09
    ắt
    -0.09
     simil
    -0.08
    entes
    -0.08
    zie
    -0.08
    _Internal
    -0.08
    /dat
    -0.08
    龸
    -0.08
    线ä¸Ĭ
    -0.08
    å°½æĥħ
    -0.08
    POSITIVE LOGITS
    失
    0.09
    è´¤
    0.09
    æľīéĻIJ责任
    0.09
    é¹ħ
    0.09
    è´ª
    0.08
    ä¸Ģ度
    0.08
    ä¸Ģå°ģ
    0.08
    ç¼ĿéļĻ
    0.08
    iesen
    0.08
    AIT
    0.08
    Activations Density 0.170%

    No Known Activations