© 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. 26455
    Prev
    Next
    INDEX
    Explanations

    celebrity surnames

    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
     ço
    -0.10
    alk
    -0.09
    éĢ»
    -0.09
    æ¼ı
    -0.09
    anks
    -0.09
    .Misc
    -0.09
    é«ĺ级
    -0.09
    ault
    -0.08
    uming
    -0.08
    deo
    -0.08
    POSITIVE LOGITS
    侬
    0.09
    åĸµ
    0.09
    é¢Ĩ
    0.09
    çĥŃ带
    0.09
    çĸijéĹ®
    0.08
    æķ·
    0.08
     Helpful
    0.08
    amp
    0.08
    åĺ²ç¬ij
    0.08
    éħĭ
    0.08
    Activations Density 0.004%

    No Known Activations