© 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. 18831
    Prev
    Next
    INDEX
    Explanations

    click, latch, lock, snap

    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
    çļĦ形象
    -0.09
    ä¸Ģæ³¢
    -0.09
    çļĦè§Ĵèī²
    -0.09
    æĤłæĤł
    -0.09
    éĺı
    -0.09
    é¹ĥ
    -0.08
    ä¸įæĺĵ
    -0.08
     Bryce
    -0.08
    iculo
    -0.08
    æŀĦçŃij
    -0.08
    POSITIVE LOGITS
     snaps
    0.10
    èĦĨ
    0.09
    åıijè¨Ģ人
    0.09
     snap
    0.09
    å²Ļ
    0.09
    ç±į
    0.09
     depress
    0.09
     snapping
    0.09
    tant
    0.09
     snapped
    0.08
    Activations Density 0.118%

    No Known Activations