© 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. 62727
    Prev
    Next
    INDEX
    Explanations

    have or has followed by a question

    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
    ucha
    -0.10
     обÑģлÑĥж
    -0.09
    对åħ¬åı¸
    -0.09
     ÑģпÑĢав
    -0.09
    INET
    -0.09
    æĮijåīĶ
    -0.09
    pé
    -0.09
    æľīéĻIJ责任
    -0.09
    uber
    -0.08
    uchar
    -0.08
    POSITIVE LOGITS
    主åĬ¨
    0.09
    issen
    0.09
    ç¾İå¾·
    0.09
    ãĥIJãĥ³
    0.09
    Oi
    0.09
    æݾ
    0.08
    踵
    0.08
    è°Ĭ
    0.08
    éĤ£å°±
    0.08
    è¡¥åħħ
    0.08
    Activations Density 0.032%

    No Known Activations