© 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. 31738
    Prev
    Next
    INDEX
    Explanations

    communicate information

    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
     cogn
    -0.09
    è®¤çŁ¥
    -0.09
     Nass
    -0.09
    .createFrom
    -0.09
    oug
    -0.08
    lop
    -0.08
    peech
    -0.08
    .signature
    -0.08
    ousse
    -0.08
    ogn
    -0.08
    POSITIVE LOGITS
    ç»Ļä½łä»¬
    0.11
    ç»Ļ大家
    0.11
    è¿Ļä¸ĢçĤ¹
    0.10
    å¾Ļ
    0.10
    REAM
    0.09
    ç»ĻæĪij们
    0.09
    åŀŃ
    0.09
    è¿ĻçĤ¹
    0.09
    rá
    0.09
    èĵĿ天
    0.08
    Activations Density 0.041%

    No Known Activations