© 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. 62965
    Prev
    Next
    INDEX
    Explanations

    along with

    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
    à¸Ńะà¹Ħร
    -0.09
    ting
    -0.09
     plat
    -0.08
    梢
    -0.08
    _align
    -0.08
    /disable
    -0.08
    emap
    -0.08
    æĪij说
    -0.08
    uÅŁ
    -0.08
    /pl
    -0.08
    POSITIVE LOGITS
    -sama
    0.13
    ãģ£ãģ¨
    0.10
    Ĺ
    0.10
    /about
    0.10
    itud
    0.09
    most
    0.09
    evity
    0.09
    人éĢł
    0.09
    ä¸ŃåĽ½åĽ½éĻħ
    0.09
    icide
    0.09
    Activations Density 0.021%

    No Known Activations