© 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. 56840
    Prev
    Next
    INDEX
    Explanations

    have something done

    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
    antz
    -0.09
    åĪ°åºķ
    -0.09
    è§īå¾Ĺ
    -0.09
    è§īå¾Ĺå¾Ī
    -0.08
    orative
    -0.08
    rece
    -0.08
    åħ·ä½ĵ
    -0.08
    è¦ģèĢĥèĻij
    -0.08
     scre
    -0.08
     Sob
    -0.08
    POSITIVE LOGITS
    æľĢéĢĤåIJĪ
    0.10
    åħ¬æ°ij
    0.10
    èݺ
    0.09
    è¶³å¤ŁçļĦ
    0.09
    éĻ¢æł¡
    0.09
    å½Ģ
    0.09
    åĽłä¸ºæĪij
    0.09
    åħįç¨İ
    0.08
    æĽ´éĢĤåIJĪ
    0.08
    çļĦåij½è¿IJ
    0.08
    Activations Density 0.081%

    No Known Activations