© 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. 4074
    Prev
    Next
    INDEX
    Explanations

    salami publishing

    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
    åIJİéĿ¢
    -0.10
     Ortiz
    -0.09
    mates
    -0.09
    åIJĦèĩª
    -0.08
    cape
    -0.08
    BREAK
    -0.08
     hữu
    -0.08
     Schultz
    -0.08
    ure
    -0.08
    eva
    -0.08
    POSITIVE LOGITS
    éĵİ
    0.10
    باء
    0.09
    åĬ¨æĦŁ
    0.09
    atial
    0.09
     Mt
    0.09
    侪
    0.09
    åĪ°æĿ¥
    0.09
    æ¿Ģæĥħ
    0.08
    èķ¤
    0.08
     Greg
    0.08
    Activations Density 0.002%

    No Known Activations