© 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. 30074
    Prev
    Next
    INDEX
    Explanations

    boat and sailing terms

    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
     Bros
    -0.11
    éķ¿å¤§äºĨ
    -0.09
    æīĺ
    -0.09
    æ©ŁéĹľ
    -0.09
    åĿł
    -0.09
    åľ°éĿ¢
    -0.09
    illis
    -0.09
     voter
    -0.09
     Corpor
    -0.09
    å¿«æ¨Ĥ
    -0.09
    POSITIVE LOGITS
    æ³Ĭ
    0.13
    çķ¸å½¢
    0.09
    èĪ¹åıª
    0.09
    .childNodes
    0.08
    çģ
    0.08
    èĪªè¡Į
    0.08
    oner
    0.08
    _scan
    0.08
    ç¨Ģ缺
    0.08
    åħ¥
    0.08
    Activations Density 0.140%

    No Known Activations