© 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. 62406
    Prev
    Next
    INDEX
    Explanations

    self-management

    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
     Arist
    -0.09
    èµ·éĩįæľº
    -0.09
    æĸ°éĻĪ代谢
    -0.09
    à¸Ńà¸Ń
    -0.09
    éĵ¸éĢł
    -0.08
    èĺħ
    -0.08
    夤
    -0.08
    æĻºéĢł
    -0.08
    侦
    -0.08
    è¡¡
    -0.08
    POSITIVE LOGITS
    èĩªåѦ
    0.21
    èĩªè¡Į
    0.20
     DIY
    0.18
    èĩªåĬ©
    0.17
     ÑģамоÑģÑĤоÑıÑĤелÑĮно
    0.16
    èĩªåĪĨãģ§
    0.16
     ÑģамоÑģÑĤоÑı
    0.13
    èĩªæĪij
    0.13
    èĩªå·±
    0.13
    DI
    0.13
    Activations Density 0.121%

    No Known Activations