© 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. 27723
    Prev
    Next
    INDEX
    Explanations

    first day

    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
    éļıæŶ
    -0.09
    erce
    -0.08
    ä»Ģä¹Īä¸ľè¥¿
    -0.08
     honor
    -0.08
    ToString
    -0.08
    ographer
    -0.08
    _LCD
    -0.08
    å¼Ģåĩº
    -0.08
    _IW
    -0.08
    ä¸įçĶĺ
    -0.08
    POSITIVE LOGITS
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.12
    маÑĢ
    0.09
    rame
    0.09
    ç¼¢
    0.09
     обÑĥÑĩениÑı
    0.09
     жизни
    0.08
    зам
    0.08
    ãģIJ
    0.08
     Barrett
    0.08
    åĴĮæĬĢæľ¯
    0.08
    Activations Density 0.036%

    No Known Activations