© 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. 59012
    Prev
    Next
    INDEX
    Explanations

    biologic behavior and potential

    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
    æµĬ
    -0.11
    ç¾İ
    -0.10
     unprotected
    -0.09
    èĭ¥æľī
    -0.08
    éľīç´ł
    -0.08
     Ñģай
    -0.08
    åħ¥åľº
    -0.08
     coarse
    -0.08
    .PO
    -0.08
    ocus
    -0.08
    POSITIVE LOGITS
    çĶŁéķ¿
    0.09
    èī¯æĢ§
    0.09
    çĶŁæ´»æĸ¹å¼ı
    0.09
     Pit
    0.09
    个æĢ§
    0.09
    _DEFIN
    0.09
    æľŁåĨħ
    0.09
    éĻ¤æѤ
    0.09
     Turnbull
    0.09
    åĿij
    0.09
    Activations Density 0.367%

    No Known Activations