© 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. 19028
    Prev
    Next
    INDEX
    Explanations

    coins and collection

    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
    ãģĩ
    -0.10
    ëĬ¥
    -0.09
     Lilly
    -0.09
    åĥı个
    -0.09
    åĿ¼
    -0.09
    ðŁı»
    -0.09
    åīįæīĢ
    -0.09
    ãģıãĤĮ
    -0.09
    òng
    -0.08
    èįij
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.11
    ä¹İ
    0.11
    egration
    0.11
    ×Ļ×ķת
    0.10
    nect
    0.10
    itial
    0.09
     toss
    0.09
    ../
    0.09
    å±ij
    0.09
    lit
    0.09
    Activations Density 0.014%

    No Known Activations