© 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. 33255
    Prev
    Next
    INDEX
    Explanations

    up to you

    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
    åı¯èĥ½æĢ§
    -0.11
     возможноÑģÑĤÑĮ
    -0.09
    å¿¿
    -0.09
    åĪĴ
    -0.08
    èĪ¬
    -0.08
    /libs
    -0.08
    anova
    -0.08
    TIM
    -0.08
     possibility
    -0.08
    igan
    -0.08
    POSITIVE LOGITS
    æ·¡åĮĸ
    0.10
    ward
    0.09
    æĪij个人
    0.09
    ä¸įä¸ĭ
    0.09
    常å§Ķ
    0.08
    æĭ±
    0.08
    empo
    0.08
    utation
    0.08
    æīĢæľī人
    0.08
    绪
    0.08
    Activations Density 0.006%

    No Known Activations