© 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. 11598
    Prev
    Next
    INDEX
    Explanations

    Concord, Letter, Chair

    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
    çİ©ç¬ij
    -0.10
    çĪµå£«
    -0.09
    åħ°èĬ±
    -0.09
    ted
    -0.09
    é²Ĥ
    -0.09
     Mens
    -0.09
    审
    -0.09
    ango
    -0.09
    ãĤ¹ãĥĿãĥ¼ãĥĦ
    -0.08
    件
    -0.08
    POSITIVE LOGITS
    åĵ¨
    0.10
    å¢ĥçķĮ
    0.09
    ÙħØŃÙħد
    0.09
    家åĽŃ
    0.08
    å±ĭéĩĮ
    0.08
    æĢ»æĶ¶åħ¥
    0.08
    ë¶Ī
    0.08
    ISTS
    0.08
    èĪĢ
    0.08
     PB
    0.08
    Activations Density 0.003%

    No Known Activations