© 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. 3692
    Prev
    Next
    INDEX
    Explanations

    Player of the Year awards

    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
    伤çĹħ
    -0.09
    ulan
    -0.08
    åħµ
    -0.08
     LoginComponent
    -0.08
    äºļ
    -0.08
     kad
    -0.08
     beat
    -0.08
    é«ĺå±Ĥ
    -0.07
    é¢Ĩ导çıŃåŃIJ
    -0.07
    çĤ¬
    -0.07
    POSITIVE LOGITS
     promise
    0.09
    à¸Ļาม
    0.09
    -worthy
    0.09
    çļĦåıijçĶŁ
    0.09
    Ø£Ùħ
    0.09
    orthy
    0.09
    çľ¨çľ¼
    0.09
    çѵ
    0.09
    çĻ¾ä¸ĩ
    0.08
    çŃīåIJĦç§į
    0.08
    Activations Density 0.006%

    No Known Activations