© 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. 34598
    Prev
    Next
    INDEX
    Explanations

    browser settings or navigation

    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
    mouth
    -0.09
    ardy
    -0.09
    æĸĹ
    -0.09
    Nib
    -0.08
    èĥľ
    -0.08
    ç®Ģ约
    -0.08
    ISTA
    -0.08
    кÑĥÑģ
    -0.08
    oes
    -0.08
    consistent
    -0.08
    POSITIVE LOGITS
    æĬ¼
    0.10
    对çĿĢ
    0.10
    ä¸įä¿¡
    0.09
    å³¥
    0.08
    çľī
    0.08
    issant
    0.08
    resses
    0.08
    /MIT
    0.08
    æŃ£å¸¸çļĦ
    0.08
    ouble
    0.08
    Activations Density 0.007%

    No Known Activations