© 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. 56711
    Prev
    Next
    INDEX
    Explanations

    redistribution and use

    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
    ä¸Ģç¬ij
    -0.09
    åIJİå¤ĩ
    -0.09
    ç»Ŀ对
    -0.08
    .getExternal
    -0.08
    éģĹæĨ¾
    -0.08
    زاÙĦ
    -0.08
    íŀĪ
    -0.08
    ayı
    -0.08
    çIJĨ念
    -0.08
     Absolute
    -0.08
    POSITIVE LOGITS
    æ´¾
    0.08
    带éĺŁ
    0.08
     poil
    0.08
    irty
    0.08
    èĭ¦
    0.08
     Mog
    0.08
    ERIC
    0.08
    åIJĨ
    0.08
    hat
    0.08
    å¢ŀè¿Ľ
    0.08
    Activations Density 0.042%

    No Known Activations