© 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. 31092
    Prev
    Next
    INDEX
    Explanations

    expressly granted or explicit casting

    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
    naire
    -0.09
    ç®Ģ称
    -0.08
    çĥŃè¡Ģ
    -0.08
    esser
    -0.08
    æļĸ
    -0.08
    oretical
    -0.08
    aur
    -0.08
    åĭĩäºİ
    -0.07
    æģ°å¥½
    -0.07
     ÑģвеÑĤ
    -0.07
    POSITIVE LOGITS
    ively
    0.12
     rÃłng
    0.12
    ely
    0.10
    mond
    0.10
    ussen
    0.09
    íŀĪ
    0.09
    .getInfo
    0.09
    ä¸įéĹ´
    0.09
    åĮºæĶ¿åºľ
    0.09
    ement
    0.09
    Activations Density 0.023%

    No Known Activations