© 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. 31028
    Prev
    Next
    INDEX
    Explanations

    colors of clothing and teams

    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
     aust
    -0.09
    æĻ°
    -0.09
    ardy
    -0.09
    _formats
    -0.09
    Sdk
    -0.08
    å¨ĩ
    -0.08
     Pé
    -0.08
     Burgess
    -0.08
     Saf
    -0.08
     Kaiser
    -0.08
    POSITIVE LOGITS
    车身
    0.09
    åĨī
    0.09
    躬
    0.09
    Ñĥни
    0.08
    çĸ«
    0.08
     Frog
    0.08
    orners
    0.08
    ä¸Ģä¼ļ
    0.08
    åħ±åĴĮ
    0.08
     pollution
    0.08
    Activations Density 0.026%

    No Known Activations