© 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. 53445
    Prev
    Next
    INDEX
    Explanations

    from where

    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
    åıŁ
    -0.10
    è´Ŀ壳
    -0.09
    è¿ĺæľīä»Ģä¹Ī
    -0.09
    ubo
    -0.09
     susp
    -0.09
    å¸Ń
    -0.08
    à¹Ĥà¸Ħร
    -0.08
    çŁŃçŁŃ
    -0.08
     windshield
    -0.08
    .QueryString
    -0.08
    POSITIVE LOGITS
    çķ¥
    0.09
     окÑĢÑĥ
    0.09
    eper
    0.08
    etes
    0.08
    yll
    0.08
    et
    0.08
    maf
    0.08
    ere
    0.08
    çĽĹ
    0.08
    èĨ¨
    0.08
    Activations Density 0.151%

    No Known Activations