© 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. 48589
    Prev
    Next
    INDEX
    Explanations

    in progress or beta versions

    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¯
    -0.10
    è²Įä¼¼
    -0.09
    åī¥
    -0.09
    å§ĭç»ĪåĿļæĮģ
    -0.09
    ä¹Łä¸įåı¯èĥ½
    -0.09
    å¤
    -0.08
    éĿ¢æĿ¿
    -0.08
    ÑģпоÑĢ
    -0.08
    ivor
    -0.08
     zost
    -0.08
    POSITIVE LOGITS
    è¿ĺä¸įæĺ¯
    0.13
    è¿ĺ没æľī
    0.13
    Beta
    0.12
     beta
    0.12
    éĽı
    0.12
     prototype
    0.11
     prototypes
    0.11
    ç²Ĺç³Ļ
    0.10
    beta
    0.10
     Beta
    0.10
    Activations Density 0.104%

    No Known Activations