© 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. 18322
    Prev
    Next
    INDEX
    Explanations

    some cases

    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
    çĻ»
    -0.09
     chances
    -0.09
    torch
    -0.09
    èijµ
    -0.09
    æĿĥ
    -0.08
    VED
    -0.08
    -wise
    -0.08
     torch
    -0.08
    ymb
    -0.08
    æ¯ĭ
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¤ľ
    0.11
    ä¸Ģé¢Ĺ
    0.10
    æ¸ł
    0.09
    ä¸ĢåĿĹ
    0.09
    éĢłè¡Ģ
    0.09
    oke
    0.09
    åħ¨åĬĽä»¥èµ´
    0.09
    æĪijåıĪ
    0.09
    ä¸Ģæĸ¹
    0.08
    ä¸Ģåįĥ
    0.08
    Activations Density 0.044%

    No Known Activations