© 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. 30868
    Prev
    Next
    INDEX
    Explanations

    heaven, hell, glory, salvation

    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
    SEN
    -0.09
    æĿ¥è¿ĻéĩĮ
    -0.09
    ç»ĿæľĽ
    -0.08
    èĩªèIJ¥
    -0.08
    å©ļ
    -0.08
    -exp
    -0.08
    å¸ľ
    -0.08
    aho
    -0.08
    æıIJæ¡Ī
    -0.08
     cord
    -0.08
    POSITIVE LOGITS
    -ready
    0.10
    æĶ¸
    0.10
     prematurely
    0.09
    ilon
    0.09
    вод
    0.09
    yo
    0.09
    大å¦Ī
    0.09
    岸
    0.09
    æ±ľ
    0.09
    ãģ©ãģĨ
    0.08
    Activations Density 0.020%

    No Known Activations