© 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. 23128
    Prev
    Next
    INDEX
    Explanations

    US states and regions

    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
    窨
    -0.10
     masc
    -0.10
    /il
    -0.09
    åľ¨é¦Ļ港
    -0.09
    åĿĬ
    -0.09
     Masc
    -0.09
    argc
    -0.09
    åıijå¸ĥåħ¬åijĬ
    -0.09
    ius
    -0.08
    å½ĵå±Ģ
    -0.08
    POSITIVE LOGITS
    inge
    0.09
    alley
    0.09
    èĿ´èĿ¶
    0.08
    æµģåIJij
    0.08
     bound
    0.08
    æĿī
    0.08
    éĽªèĬ±
    0.08
    zing
    0.08
    èĮ¶
    0.08
    bound
    0.08
    Activations Density 0.005%

    No Known Activations