© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    Palmyra, myra, divoxetine

    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
    mes
    -0.10
    ados
    -0.10
    ado
    -0.09
    tings
    -0.09
    çĥ¹
    -0.09
    çıı
    -0.09
    wed
    -0.09
    NBC
    -0.08
    sid
    -0.08
    문
    -0.08
    POSITIVE LOGITS
    à¸Ńà¸Ķ
    0.09
    èĥ¸éĥ¨
    0.09
    ç¢ij
    0.09
    esan
    0.09
    åĪ©çĽĬ
    0.08
    azo
    0.08
    åŀĤ
    0.08
    æ©Ħ
    0.08
    çļĩåIJİ
    0.08
     Autom
    0.08
    Activations Density 0.003%

    No Known Activations