© 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. 23078
    Prev
    Next
    INDEX
    Explanations

    blog comments and subscriptions

    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
     reb
    -0.08
    èįł
    -0.08
    .pad
    -0.08
    emer
    -0.07
    og
    -0.07
    mie
    -0.07
    lock
    -0.07
    nam
    -0.07
    å¦ĤæĦı
    -0.07
     Paid
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.11
    å¸ļ
    0.09
     Trouble
    0.09
    ä¼´
    0.09
    itte
    0.09
     Troll
    0.08
    ç½ijé¦ĸ页
    0.08
    ç´§è·Ł
    0.08
    åħ¨éĿ¢åıijå±ķ
    0.08
     Jen
    0.08
    Activations Density 0.007%

    No Known Activations