© 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. 37868
    Prev
    Next
    INDEX
    Explanations

    University Press, Momentum Press

    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
     retro
    -0.08
    åĨ²éĶĭ
    -0.08
    SCR
    -0.08
    è°ı
    -0.08
     Welcome
    -0.08
    à¹Ģà¸Ĺà¸ŀ
    -0.08
    寮
    -0.08
    é¦Ļæ°´
    -0.08
    (Art
    -0.08
    .man
    -0.07
    POSITIVE LOGITS
    åĩºçīĪ社
    0.11
    è¥Ħ
    0.10
    รว
    0.10
    éĶ²
    0.09
    ç±´
    0.09
    å°ijéĩı
    0.09
    rice
    0.09
     upt
    0.09
    _lifetime
    0.09
    çijķ
    0.09
    Activations Density 0.062%

    No Known Activations