© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    languages and linguistics

    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
    çĭ»
    -0.10
    çŃ¹éĽĨ
    -0.10
    æķĽ
    -0.09
    ç»
    -0.09
    ofil
    -0.08
    è´·
    -0.08
    -svg
    -0.08
    象
    -0.08
    åįıåIJĮ
    -0.08
    strup
    -0.08
    POSITIVE LOGITS
    åıijéŁ³
    0.12
    åIJ¬åĬĽ
    0.12
    æĸ¹è¨Ģ
    0.11
    æ±īè¯Ń
    0.11
    çļĦè¯Ńè¨Ģ
    0.11
    æĸĩåĮĸ交æµģ
    0.11
    交éĻħ
    0.10
    ilingual
    0.10
    è¯įæ±ĩ
    0.10
    ç¿»è¯ij
    0.09
    Activations Density 0.396%

    No Known Activations