© 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. 36160
    Prev
    Next
    INDEX
    Explanations

    be released / part / contacted

    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
    etti
    -0.09
     Brit
    -0.09
    izzo
    -0.09
    对åħ¶
    -0.08
    reopen
    -0.08
    èĩ
    -0.08
    shal
    -0.08
    ä¸įå¼Ģ
    -0.08
    åĪĹ为
    -0.08
    ted
    -0.08
    POSITIVE LOGITS
    å·¥åķĨ
    0.09
    imon
    0.09
    jing
    0.09
     Marr
    0.08
     ÐľÐ¾ÑģквÑĭ
    0.08
    åŃļ
    0.08
    åĽ½å®ī
    0.08
    _DIP
    0.08
    ?url
    0.08
    å¾Ī好
    0.08
    Activations Density 0.111%

    No Known Activations