© 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. 32947
    Prev
    Next
    INDEX
    Explanations

    letters followed by numbers

    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
    èĢģæĿ¿
    -0.09
    å¤ĸåĽ´
    -0.09
    ele
    -0.09
    udem
    -0.09
    è¿ĻèĪ¬
    -0.08
    eur
    -0.08
    ye
    -0.08
    éķ¿èĢģ
    -0.08
    atto
    -0.08
    jem
    -0.08
    POSITIVE LOGITS
    以ä¸ĬçļĦ
    0.09
    standing
    0.08
     cui
    0.08
     trá»Ŀi
    0.08
    alog
    0.08
    ä¸Ģ大æī¹
    0.08
    ä¿IJ
    0.08
    tempts
    0.08
    undreds
    0.08
    conds
    0.08
    Activations Density 0.392%

    No Known Activations