© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21906
    Prev
    Next
    INDEX
    Explanations

    legislative body names

    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
    çªĿ
    -0.11
    éĻ·
    -0.09
    å¼łè´´
    -0.09
     Dip
    -0.09
    åľ¨å½ĵåľ°
    -0.08
    oho
    -0.08
    ç¿ł
    -0.08
    éĹ®è´£
    -0.08
     Fade
    -0.08
    ç
    -0.08
    POSITIVE LOGITS
    åħ¸
    0.09
     dash
    0.09
    alice
    0.09
    å·©
    0.09
    algo
    0.09
    è´Ł
    0.09
    aturing
    0.08
    tran
    0.08
    ignet
    0.08
     Mentor
    0.08
    Activations Density 0.056%

    No Known Activations