© 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. 56275
    Prev
    Next
    INDEX
    Explanations

    voting and 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
    yne
    -0.09
    çĪ±ç¾İ
    -0.09
    åĤ»
    -0.09
    jur
    -0.09
    piel
    -0.08
    usu
    -0.08
    è¾ķ
    -0.08
    ĥģ
    -0.08
    åĮ»æĬ¤
    -0.08
    红æĺŁ
    -0.08
    POSITIVE LOGITS
     Parr
    0.09
    æµı
    0.09
    çݳ
    0.08
    è·Ĺ
    0.08
    éĹ¨æ§Ľ
    0.08
    ðŁĺĢ
    0.08
    resco
    0.08
    rophy
    0.08
    å¤ļåľ°
    0.08
    robe
    0.08
    Activations Density 0.025%

    No Known Activations