© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37810
    Prev
    Next
    INDEX
    Explanations

    chiropractor introducing stress leakage

    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
    管
    -0.09
    itur
    -0.08
    ifr
    -0.08
    .lua
    -0.08
    oku
    -0.08
    æ»´
    -0.08
    æµģ转
    -0.08
    CallBack
    -0.08
     Dank
    -0.08
     Kou
    -0.08
    POSITIVE LOGITS
     Scientology
    0.12
    å·¥ä½ľç«Ļ
    0.09
    è¾Ħ
    0.09
    ç®´
    0.09
    线ä¸ĭ
    0.09
     troch
    0.08
     Scient
    0.08
    æĬµ
    0.08
    osoph
    0.08
    ODO
    0.08
    Activations Density 0.069%

    No Known Activations