© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    locations following "in"

    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
     vs
    -0.09
    _vs
    -0.09
    ä¹ĭ乡
    -0.08
     пÑĢож
    -0.08
    çĸijéĹ®
    -0.08
    æĶ¾åľ¨
    -0.08
    /wiki
    -0.08
    履约
    -0.08
    ufe
    -0.07
    å¹½é»ĺ
    -0.07
    POSITIVE LOGITS
    /of
    0.11
    ä¸įæİĴéĻ¤
    0.10
    å®Ļ
    0.10
    æĺ¯åĽ½åĨħ
    0.10
    衬
    0.09
    ä¸Ģ头
    0.09
    æĸ°ä¸ī
    0.09
    çł
    0.09
    uchs
    0.09
    rint
    0.08
    Activations Density 0.124%

    No Known Activations