© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38266
    Prev
    Next
    INDEX
    Explanations

    hell on Wheels, Hellboy, Hell Pizza, Hell's Kitchen

    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
    黯
    -0.09
    atis
    -0.08
    åŁ¹
    -0.08
    çĥŁçģ«
    -0.08
    æł¼å¤ĸ
    -0.08
    atism
    -0.08
    insic
    -0.07
    ä»İèĢĮ
    -0.07
    éģĵ
    -0.07
    uple
    -0.07
    POSITIVE LOGITS
    åıijå±ķéĺ¶æ®µ
    0.11
    追éĹ®
    0.11
    ddit
    0.10
    åĵī
    0.10
    è¿ĺæľīå¾Īå¤ļ
    0.10
    æľīç§į
    0.09
    ories
    0.09
    icious
    0.09
     egt
    0.09
    ç¦ıçī¹
    0.09
    Activations Density 0.002%

    No Known Activations