© 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. 49290
    Prev
    Next
    INDEX
    Explanations

    length constraints

    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
    å¸ĸåŃIJ
    -0.09
    ighet
    -0.09
    .reducer
    -0.08
    çĿĩ
    -0.08
     coff
    -0.08
    .tpl
    -0.08
    è¯Ŀé¢ĺ
    -0.08
    izzo
    -0.08
    ROI
    -0.08
    è¡£æľį
    -0.08
    POSITIVE LOGITS
    alt
    0.09
    erti
    0.09
    <<
    0.08
    å»īæĶ¿
    0.08
    家éŨåı£
    0.08
    æīİæł¹
    0.08
    åĿļæĮģ
    0.08
    èĮĢ
    0.08
    æīĵå¾Ĺ
    0.08
    认åı¯
    0.08
    Activations Density 0.034%

    No Known Activations