© 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. 39441
    Prev
    Next
    INDEX
    Explanations

    practice and guidelines

    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
    èĭĩ
    -0.10
    åŃ£
    -0.09
    å±±åİ¿
    -0.09
    åıijå±ķ模å¼ı
    -0.08
     plate
    -0.08
    plate
    -0.08
    isms
    -0.08
    ibox
    -0.08
    aben
    -0.08
    è½
    -0.08
    POSITIVE LOGITS
    å®ŀè·µ
    0.18
    å®ŀè·µä¸Ń
    0.15
     practice
    0.14
    å®ŀ践活åĬ¨
    0.14
    è¡ĮåĬ¨
    0.13
     пÑĢакÑĤи
    0.12
     Practice
    0.12
     pratique
    0.12
     prakt
    0.11
    å®ŀåĬ¡
    0.11
    Activations Density 0.086%

    No Known Activations