© 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. 23909
    Prev
    Next
    INDEX
    Explanations

    Jark Matter, Gorizbadd, Remhora

    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
    å®Ŀè´Ŀ
    -0.09
    亲çĪ±
    -0.09
     chir
    -0.09
    çĪĨåĩº
    -0.09
    éľ¹
    -0.09
    æĥł
    -0.09
     chop
    -0.08
    èĭŀ
    -0.08
    çĮ¿
    -0.08
    æĪIJ绩
    -0.08
    POSITIVE LOGITS
     обла
    0.10
    èĮĦ
    0.09
    odon
    0.09
    ä¸įåı¯æĢĿ
    0.08
    bane
    0.08
    ัย
    0.08
     Airlines
    0.08
    UMMY
    0.08
    uther
    0.08
    èĥ½æºIJ
    0.08
    Activations Density 0.070%

    No Known Activations