© 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. 55569
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases with proper nouns or specific terms

    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
    yped
    -0.09
    åľ¨éĩĮéĿ¢
    -0.09
    è¿ĩåIJİ
    -0.08
    /OR
    -0.08
    DITION
    -0.08
     заÑĤем
    -0.08
    ZF
    -0.08
    oy
    -0.08
    ç¼µ
    -0.08
    æľī大éĩıçļĦ
    -0.08
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.10
    /from
    0.09
    é»Ħèī²
    0.09
    sembl
    0.08
    иде
    0.08
    oppers
    0.08
    丧失
    0.08
    odom
    0.08
    第ä¸Ģå±Ĭ
    0.08
    иÑĨе
    0.08
    Activations Density 0.293%

    No Known Activations