© 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. 63414
    Prev
    Next
    INDEX
    Explanations

    structured questionnaire or interview

    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
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.10
    å¹¿æ³Ľ
    -0.10
    itch
    -0.09
    æĬ
    -0.09
    é©¿
    -0.08
    以人为
    -0.08
    æīģ
    -0.08
    温馨æıIJ示
    -0.08
    arry
    -0.08
     Sporting
    -0.08
    POSITIVE LOGITS
    æĢ§å¼º
    0.11
    ness
    0.10
    æijĨåľ¨
    0.09
    è°¨
    0.09
    龸æ°Ķ
    0.09
    orum
    0.09
    ç¾İæĦŁ
    0.09
    è¿ĺä¸įå¤Ł
    0.08
    严谨
    0.08
    èľĢ
    0.08
    Activations Density 0.055%

    No Known Activations