© 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. 34009
    Prev
    Next
    INDEX
    Explanations

    decimal numbers with slashes

    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¯ī
    -0.09
    æī¾å·¥ä½ľ
    -0.09
    ä¿©
    -0.09
    /or
    -0.08
    uring
    -0.08
    æĹłæķ°
    -0.08
    amp
    -0.08
     others
    -0.08
    azes
    -0.08
    å¼łå®¶åı£
    -0.08
    POSITIVE LOGITS
    ovo
    0.10
    -scrollbar
    0.10
    ÑģÑĮ
    0.10
    ãģ¤ãģį
    0.10
    IGO
    0.10
    esty
    0.09
    ÑĢажа
    0.09
    åľ¨å®¶
    0.09
    igo
    0.09
    alty
    0.09
    Activations Density 0.104%

    No Known Activations