© 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. 17939
    Prev
    Next
    INDEX
    Explanations

    stop or limit

    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
    gar
    -0.09
    éĥ½åĸľæ¬¢
    -0.08
    ä»Ģä¹Īæł·çļĦ
    -0.08
    æĶĢçĻ»
    -0.08
    åĸĩ
    -0.08
    æĹłæīĢè°ĵ
    -0.08
     Lá»ĭch
    -0.08
    Syntax
    -0.08
    ä¸ĭåįĬ
    -0.08
    çĴł
    -0.08
    POSITIVE LOGITS
    åģľçķĻåľ¨
    0.14
    åĪ°è¿ĻéĩĮ
    0.11
    ä¸įæŃ¢
    0.11
    åģľçķĻ
    0.10
    igli
    0.10
    å±ĢéĻIJäºİ
    0.10
    åģľ
    0.10
    åģľä¸ĭ
    0.10
    ä»ħä»ħ
    0.09
    _stop
    0.09
    Activations Density 0.026%

    No Known Activations