© 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. 58957
    Prev
    Next
    INDEX
    Explanations

    types or kinds of

    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
    åħį
    -0.10
    æIJĶ
    -0.09
    ä¹IJåĽŃ
    -0.09
    足
    -0.09
    ifu
    -0.09
    wap
    -0.08
    ying
    -0.08
    ió
    -0.08
    ä¸ĩ家
    -0.08
    äºĨä¸ĢäºĽ
    -0.08
    POSITIVE LOGITS
    ç±»åŀĭçļĦ
    0.15
     types
    0.10
     kinds
    0.09
    _PCM
    0.09
    _types
    0.09
    alem
    0.09
    ç±»åŀĭ
    0.09
    -types
    0.09
    aju
    0.09
    /types
    0.09
    Activations Density 0.076%

    No Known Activations