© 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. 62069
    Prev
    Next
    INDEX
    Explanations

    travel destinations, agents, and packages

    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
    strap
    -0.10
    sten
    -0.10
    æĶ¶è´¹ç«Ļ
    -0.09
     Lager
    -0.09
    CADE
    -0.09
    èĭ
    -0.09
    çŁ³æ²¹åĮĸå·¥
    -0.09
    sWith
    -0.09
    ä¾ĽéĶĢ
    -0.09
    çŃĴ
    -0.08
    POSITIVE LOGITS
    ä¸Ģè¶Ł
    0.14
    æĶ»çķ¥
    0.13
    æĹħ游
    0.13
    æĹħè¡Į社
    0.13
    è¡Įç¨ĭ
    0.12
    导游
    0.12
    æĹħè¡Į
    0.11
    线路
    0.11
    æĬ¤çħ§
    0.11
     кÑĢÑĥ
    0.11
    Activations Density 0.130%

    No Known Activations