© 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. 23042
    Prev
    Next
    INDEX
    Explanations

    working with

    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
     mim
    -0.10
    ä½ľåĵģ
    -0.09
    顺
    -0.09
    nap
    -0.09
    份
    -0.09
    åĪ¶éĢł
    -0.09
    çIJĨ论ä¸Ĭ
    -0.08
    建ç«ĭåģ¥åħ¨
    -0.08
     Guil
    -0.08
    æĥ¬
    -0.08
    POSITIVE LOGITS
    aho
    0.09
    Ñıн
    0.09
    å¿ĺ
    0.09
     relationship
    0.08
    é½IJ
    0.08
    é²Ł
    0.08
    è¯Ĥ
    0.08
    تÙĨ
    0.08
    _VOL
    0.08
    åħ³ç³»
    0.08
    Activations Density 0.032%

    No Known Activations