© 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. 30695
    Prev
    Next
    INDEX
    Explanations

    Godsmack lyrics

    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
    éĻ¢éĻ¢éķ¿
    -0.09
    _ROUT
    -0.09
    大åѦæ¯ķä¸ļ
    -0.08
    éo
    -0.08
    çıį
    -0.08
    å®Łãģ¯
    -0.08
    éĶº
    -0.08
    gow
    -0.08
    空åīį
    -0.08
    åı½
    -0.07
    POSITIVE LOGITS
    åĴ«
    0.09
     ØŃÙĤ
    0.09
    寸
    0.08
     Thousand
    0.08
    éŀŃ
    0.08
    ä¸Ģä¸ĸ
    0.08
    .Toolkit
    0.08
    /Foundation
    0.08
    казан
    0.08
    edly
    0.08
    Activations Density 0.438%

    No Known Activations