© 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. 23584
    Prev
    Next
    INDEX
    Explanations

    plasticity

    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
    æ³ķ令
    -0.09
    ledge
    -0.09
     лÑĥÑĩÑĪиÑħ
    -0.09
    ä¹ĭä½ľ
    -0.09
    edly
    -0.08
    BEST
    -0.08
    wd
    -0.08
    ocol
    -0.08
    è°´
    -0.08
     quest
    -0.08
    POSITIVE LOGITS
    ity
    0.11
    翼
    0.11
    å¡ij
    0.10
    è¿Ļ段
    0.09
    çİ°åĩº
    0.09
    éĵ¤
    0.09
    åģ¥åħ¨
    0.09
    è¿ĩ硬
    0.09
    åĩłå¼ł
    0.09
    даÑĢ
    0.09
    Activations Density 0.054%

    No Known Activations