© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21822
    Prev
    Next
    INDEX
    Explanations

    budget deal, cuts, proposal, items

    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¡Įä¸ļçļĦ
    -0.10
    人éĢł
    -0.09
    åĽ´æ£ĭ
    -0.09
    æīĢåľ¨
    -0.08
    åľ¨æ·±åľ³
    -0.08
    ç§ī
    -0.08
    åľ¨æĹ¥æľ¬
    -0.08
    /aws
    -0.08
    æłĩéħį
    -0.08
    AGED
    -0.08
    POSITIVE LOGITS
    otts
    0.10
    æĿĸ
    0.09
    åħĶ
    0.09
    éĻ½
    0.08
    dish
    0.08
    亨
    0.08
    ature
    0.08
    绦
    0.08
     Bellev
    0.08
    Interop
    0.07
    Activations Density 0.006%

    No Known Activations