© 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. 55340
    Prev
    Next
    INDEX
    Explanations

    roasting, hating, salty, piss-taking, taunting, abuse

    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
    usra
    -0.09
     Wolfe
    -0.09
    .pad
    -0.09
     knot
    -0.09
    åıĤèĢĥèµĦæĸĻ
    -0.08
    åģĩæľŁ
    -0.08
    andro
    -0.08
    åľĸ
    -0.08
    ç´¢
    -0.08
    ãĤĴè¦ĭãģĽ
    -0.08
    POSITIVE LOGITS
    _relations
    0.08
    åĪļ
    0.08
    è¿ĩ
    0.08
    身价
    0.08
    \$
    0.08
    天èĬ±æĿ¿
    0.08
    å½ĵåľº
    0.08
    asti
    0.08
     vak
    0.07
    使çĶ¨èĢħæĪĸ
    0.07
    Activations Density 0.012%

    No Known Activations