© 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. 39151
    Prev
    Next
    INDEX
    Explanations

    limit, minimum, requirement

    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
    åĨµä¸Ķ
    -0.10
    æī¹å¤į
    -0.10
    æİĮ
    -0.09
    æļĩ
    -0.09
    çijķ
    -0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.09
    管ç½ij
    -0.09
    æİ¥æīĭ
    -0.09
    (keys
    -0.09
    éī´
    -0.08
    POSITIVE LOGITS
    éĻIJåĪ¶
    0.20
     огÑĢани
    0.16
    è¦ģæ±Ĥ
    0.16
     limit
    0.16
     limits
    0.14
     limitations
    0.14
    éĻIJ度
    0.14
    éĻIJ
    0.14
     requirement
    0.14
    ä¸ĬéĻIJ
    0.14
    Activations Density 0.101%

    No Known Activations