© 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. 31519
    Prev
    Next
    INDEX
    Explanations

    pay for services

    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
     Dum
    -0.09
    ç¬ķ
    -0.09
    SourceType
    -0.09
    æľīå¾ħ
    -0.08
    éĢłä»·
    -0.08
    èŀŃ
    -0.08
    å¤įä»ĩ
    -0.08
    annah
    -0.08
    ARA
    -0.08
    stra
    -0.08
    POSITIVE LOGITS
    åĬ³åĬ¡
    0.10
    代
    0.09
    æħĿ
    0.09
    å¼Ĭ
    0.09
    妾
    0.08
    ä¸ĵ享
    0.08
    带æĿ¥æĽ´å¤ļ
    0.08
    èĨ¦
    0.08
    çĬ¯
    0.08
    ä¸įæ¸ħ
    0.08
    Activations Density 0.059%

    No Known Activations