© 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. 22515
    Prev
    Next
    INDEX
    Explanations

    includes a list

    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
    è¿ĩå¾Ģ
    -0.10
    æ²¹æ¼Ĩ
    -0.10
    ä¸ĢåĪĨéĴ±
    -0.09
    æ®Ĩ
    -0.09
    åľ¨è¿Ļ
    -0.09
    çĩĥ
    -0.09
    æĤ¨å¥½
    -0.09
    liÄŁini
    -0.09
    Synopsis
    -0.09
    çŁ¥æĻĵ
    -0.09
    POSITIVE LOGITS
    ä¸ī项
    0.09
    yan
    0.08
    ä¸ī个
    0.08
    åĽĽä¸ª
    0.08
    诸å¤ļ
    0.08
    mute
    0.08
    aber
    0.08
     provisions
    0.08
    odu
    0.08
    three
    0.08
    Activations Density 0.077%

    No Known Activations