© 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. 35509
    Prev
    Next
    INDEX
    Explanations

    hand signals and gestures

    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
    ãĤ³ãĥŁ
    -0.11
    严èĤĥ
    -0.09
     displacement
    -0.08
     neur
    -0.08
    esser
    -0.08
    è±³
    -0.08
    åħħæ²Ľ
    -0.08
    Disappear
    -0.08
    èĩªæĦ¿
    -0.08
    åħ¨æĸ°çļĦ
    -0.08
    POSITIVE LOGITS
    示æĦı
    0.15
    ä¸Ģç¬ij
    0.09
    ä¼Ļä¼´
    0.08
    çĽ¼
    0.08
     Solo
    0.08
     meaning
    0.08
    ç§ĺ书éķ¿
    0.08
    è°ĥåĬ¨
    0.08
    åij¼åºĶ
    0.08
    LD
    0.08
    Activations Density 0.017%

    No Known Activations