© 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. 35185
    Prev
    Next
    INDEX
    Explanations

    large size

    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¢ħ
    -0.09
    水管
    -0.08
    eri
    -0.08
    çĶļ
    -0.08
    æıŃ
    -0.08
    responsive
    -0.08
    odem
    -0.08
    èݪ
    -0.08
    traits
    -0.08
    ç¬ĭ
    -0.08
    POSITIVE LOGITS
    大çļĦ
    0.10
    大ãģįãģª
    0.09
     drafts
    0.08
    -grand
    0.08
    erval
    0.08
    ä¸įæĸ¹ä¾¿
    0.08
    mans
    0.08
    æĬĬå®ĥ
    0.08
    à¹ģà¸Ł
    0.08
    uge
    0.08
    Activations Density 0.039%

    No Known Activations