© 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. 57478
    Prev
    Next
    INDEX
    Explanations

    not

    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
    ä¸Ńå°ıåŀĭ
    -0.09
    illon
    -0.08
    çIJ¥
    -0.08
    èĤ¯
    -0.08
    å®īåİ¿
    -0.08
    dos
    -0.08
    ä¸įåı¯
    -0.08
    èĢ¸
    -0.08
    è¡£
    -0.08
    nap
    -0.08
    POSITIVE LOGITS
    ä¹Łæ²¡
    0.14
    ä¹Łä¸įèĥ½
    0.13
    ä¹Łæ²¡æľī
    0.12
    ä¹Łä¸į
    0.11
    ä¹Łæ²¡ä»Ģä¹Ī
    0.10
    ä¹Łä¸įåı¯èĥ½
    0.10
    éĺ²èĮĥ
    0.09
    æĪijä¹Ł
    0.09
    ä¹Łä¸įè¦ģ
    0.09
     McCorm
    0.09
    Activations Density 0.024%

    No Known Activations