© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7138
    Prev
    Next
    INDEX
    Explanations

    door closed

    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
    åħ¬è·¯
    -0.09
    å®ħ
    -0.09
     road
    -0.09
    è§ģ解
    -0.09
    驱
    -0.09
    溯
    -0.08
    人å±ħ
    -0.08
     Road
    -0.08
    éĵº
    -0.08
    æ²ī
    -0.08
    POSITIVE LOGITS
    å¢ĻéĿ¢
    0.10
    .anim
    0.10
    ä¸ĬçıŃæĹı
    0.10
     Duffy
    0.09
     ëĪĦ
    0.09
    ajs
    0.09
    ä¸Ģç«Ļ
    0.09
    大å®Ĺ
    0.09
    ä¹ĺ客
    0.09
    天èĬ±
    0.09
    Activations Density 0.059%

    No Known Activations