© 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. 4975
    Prev
    Next
    INDEX
    Explanations

    fast and very

    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
    诳
    -0.10
     EITHER
    -0.10
    gli
    -0.09
    .tc
    -0.09
    á»ļ
    -0.09
    ãģ¼
    -0.09
     VE
    -0.09
    /rfc
    -0.08
    NX
    -0.08
    rouw
    -0.08
    POSITIVE LOGITS
    æĢ§å¼º
    0.09
    åĢ¡
    0.08
    管å§Ķä¼ļ
    0.08
    竽
    0.08
    _lens
    0.08
     mojo
    0.08
    èĤ¡
    0.08
    aju
    0.08
    akis
    0.08
    UDO
    0.08
    Activations Density 0.113%

    No Known Activations