© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21982
    Prev
    Next
    INDEX
    Explanations

    vendor promise

    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
    phia
    -0.10
     оÑĤд
    -0.10
     пÑĢоÑģ
    -0.09
    illez
    -0.09
    OrNil
    -0.08
    .orm
    -0.08
    asured
    -0.08
     Reliable
    -0.08
    æ²īéĩį
    -0.08
    à¹ģร
    -0.08
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.12
    èĢĮå·²
    0.11
    ä¹ĭ举
    0.10
    ä»ħ代表
    0.10
    è¥ģ
    0.09
    æ³±
    0.09
    ç½¢äºĨ
    0.09
    ä¸į代表
    0.09
    太ä¹ħ
    0.09
    ALAR
    0.09
    Activations Density 0.084%

    No Known Activations