© 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. 49520
    Prev
    Next
    INDEX
    Explanations

    needs and requirements

    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
    _INITIALIZER
    -0.09
    诣
    -0.09
    é¢ĨæĤŁ
    -0.09
    çĸĥ
    -0.09
    handled
    -0.09
    è®¤çľŁèIJ½å®ŀ
    -0.09
    ä¸Ģåı¥è¯Ŀ
    -0.08
    .Take
    -0.08
    æIJı
    -0.08
    çĥŃéŨ
    -0.08
    POSITIVE LOGITS
    è¦ģæ±Ĥ
    0.11
    çļĦè¦ģæ±Ĥ
    0.11
    å¸ĤåľºéľĢæ±Ĥ
    0.10
     requirements
    0.10
    缮çļĦ
    0.09
     needs
    0.09
     standards
    0.09
     criteria
    0.09
     ÑĤÑĢебованиÑı
    0.09
    æĹ¢è¦ģ
    0.09
    Activations Density 0.051%

    No Known Activations