© 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. 50689
    Prev
    Next
    INDEX
    Explanations

    return original container

    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
    .Serve
    -0.10
    hell
    -0.10
    åIJĦä½į
    -0.09
    头èĦij
    -0.09
    ocy
    -0.09
     ниÑĩ
    -0.08
    ë²Ķ
    -0.08
    次æķ°
    -0.08
    ODB
    -0.08
    çª
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įè¦ģ
    0.12
    å®ĵ
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    ä»Ģä¹Īåľ°æĸ¹
    0.09
     Goth
    0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    0.09
    亲èĩª
    0.09
    åįĸæİī
    0.09
    èµ°
    0.08
    è§Ħ模æľĢ大
    0.08
    Activations Density 0.009%

    No Known Activations