© 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. 17002
    Prev
    Next
    INDEX
    Explanations

    practice or training facility

    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
    æ§Ľ
    -0.10
    CORE
    -0.10
    åı¬
    -0.10
    icap
    -0.09
    _mC
    -0.09
    TRS
    -0.09
    Locker
    -0.09
    (gc
    -0.09
    antro
    -0.09
    缴åįĩ
    -0.09
    POSITIVE LOGITS
    ç»ĥä¹ł
    0.18
    è®Ńç»ĥ
    0.17
     training
    0.14
    è¨ĵç·´
    0.13
    模æĭŁ
    0.13
    æ¼Ķç»ĥ
    0.13
    ç»ĥ
    0.12
     Training
    0.12
    ç·´
    0.12
    åľºåľ°
    0.11
    Activations Density 0.114%

    No Known Activations