© 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. 28043
    Prev
    Next
    INDEX
    Explanations

    sagging, slack, sagittal, ptosis

    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
    æ¿Ģ
    -0.10
    UMP
    -0.09
    çIJħ
    -0.09
    åĵĦ
    -0.09
    æĺ§
    -0.09
    iais
    -0.09
    迳
    -0.09
    è¢į
    -0.09
    bris
    -0.09
    ä¾
    -0.08
    POSITIVE LOGITS
    ä¸įåłª
    0.11
    sWith
    0.10
    è´¢æĶ¿
    0.09
    ingly
    0.09
    åŀĤ
    0.08
    ord
    0.08
    éĹ¾
    0.08
    综åIJĪå¾ģ
    0.08
    ez
    0.08
    eo
    0.08
    Activations Density 0.018%

    No Known Activations