© 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. 63268
    Prev
    Next
    INDEX
    Explanations

    biographical introductions

    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
    å¤į
    -0.09
    æīĵåĩ»
    -0.09
    ye
    -0.09
     Sap
    -0.08
    忽
    -0.08
     Stuart
    -0.07
     cigarettes
    -0.07
     fmt
    -0.07
    寡
    -0.07
    atto
    -0.07
    POSITIVE LOGITS
    ä»ĭç»į
    0.17
    ä»ĭç´¹
    0.15
    ä»ĭç»įä¸Ģä¸ĭ
    0.15
    ä»ĭç»į说
    0.13
    ç®Ģä»ĭ
    0.13
    详ç»Ĩä»ĭç»į
    0.13
     profiles
    0.13
    ä»ĭç»įäºĨ
    0.12
    ibel
    0.11
    /profile
    0.11
    Activations Density 0.081%

    No Known Activations