© 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. 54772
    Prev
    Next
    INDEX
    Explanations

    Long Short-Term Memory, Hidden Markov Models, automata

    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
    æŀ¶
    -0.10
     Paint
    -0.10
    èĥ¶
    -0.10
    éĺ¶å±Ĥ
    -0.10
    æĦ¿æĻ¯
    -0.09
    _malloc
    -0.09
     Vision
    -0.09
    Vision
    -0.09
    çľĭæ³ķ
    -0.09
    线ä¸Ĭ线ä¸ĭ
    -0.09
    POSITIVE LOGITS
     Cah
    0.10
    corr
    0.09
    ilon
    0.09
    读书
    0.09
     STD
    0.09
    èĥ½åĬĽå¼º
    0.09
    ä¸ºæł¸å¿ĥçļĦ
    0.09
    اÙĦÙħع
    0.08
    澡
    0.08
    è³ĵ
    0.08
    Activations Density 0.150%

    No Known Activations