© 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. 7409
    Prev
    Next
    INDEX
    Explanations

    don't care

    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
     ByteArray
    -0.09
    çļ®éĿ©
    -0.09
    峤
    -0.09
    诡
    -0.08
    èį»
    -0.08
    ValuePair
    -0.08
    çķ¸å½¢
    -0.08
    à¹īà¸Ńย
    -0.08
    abler
    -0.08
    JNI
    -0.08
    POSITIVE LOGITS
    orate
    0.10
    aning
    0.09
     Kane
    0.09
    çĩ¥
    0.08
    èĽĭ
    0.08
     ander
    0.08
    ersen
    0.08
    èºģ
    0.08
    æľīä»»ä½ķ
    0.08
     ISSN
    0.08
    Activations Density 0.147%

    No Known Activations