© 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. 39805
    Prev
    Next
    INDEX
    Explanations

    if conditional followed by action

    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
    夫
    -0.09
    ava
    -0.09
    éĤ£æŶåĢĻ
    -0.08
    å¾Īå¤ļäºĭæĥħ
    -0.08
     underst
    -0.08
    ufen
    -0.08
    esso
    -0.07
    并ä¸įæĺ¯å¾Ī
    -0.07
    æľīå¾Ī大çļĦ
    -0.07
     dialogRef
    -0.07
    POSITIVE LOGITS
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    0.17
    ä¸įå¾Ĺå·²
    0.16
    ä¸įåı¯éģ¿åħį
    0.16
    å®ŀåľ¨
    0.12
    è¿ĺæĺ¯è¦ģ
    0.11
    æĽ´è¦ģ
    0.10
     unavoidable
    0.10
    èĥ½åģļåĪ°
    0.10
    çīĮ
    0.10
    临æŶ
    0.09
    Activations Density 0.044%

    No Known Activations