© 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. 30011
    Prev
    Next
    INDEX
    Explanations

    limited, restrictions, or bounds

    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
    åħ¼
    -0.10
    orgh
    -0.10
    修士
    -0.10
    鼳
    -0.09
    禾
    -0.09
    åİŁæĸĩåľ°åĿĢ
    -0.09
    æĸ°éĹ»è®°èĢħ
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    èĩªæ²»
    -0.09
    usch
    -0.09
    POSITIVE LOGITS
    æĿŁç¼ļ
    0.19
    éĻIJåĪ¶
    0.18
     огÑĢани
    0.15
    约æĿŁ
    0.14
    æĭĺ
    0.14
     constraints
    0.14
    å±ĢéĻIJäºİ
    0.13
     restrictions
    0.13
    å±ĢéĻIJ
    0.13
    æ¡İ
    0.13
    Activations Density 0.064%

    No Known Activations