© 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. 55371
    Prev
    Next
    INDEX
    Explanations

    field trips

    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
    庵
    -0.10
    åħ¥åĽŃ
    -0.10
    æľīåIJį
    -0.09
    _ascii
    -0.09
    æĤ¬å¿µ
    -0.08
    hton
    -0.08
    è¾¾æĪIJ
    -0.08
    åıijæī¬
    -0.08
    帮æĪij
    -0.08
    и
    -0.08
    POSITIVE LOGITS
    ä¸ĢæĶ¯
    0.11
    ering
    0.09
    æµ·å¤ĸå¸Ĥåľº
    0.09
    â½´
    0.09
    çIJ³
    0.09
     ÑĢÑĥк
    0.09
    è®°èĢħéĩĩ访
    0.09
    erable
    0.09
    èı©æıIJ
    0.09
    碴
    0.09
    Activations Density 0.004%

    No Known Activations