© 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. 49580
    Prev
    Next
    INDEX
    Explanations

    me

    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
    ahren
    -0.10
    OLT
    -0.10
    oked
    -0.09
    æľ½
    -0.09
    è¿Ļ对äºİ
    -0.09
    обÑĢа
    -0.09
    ä»ĸä¼ļ
    -0.09
    нÑıÑĤ
    -0.09
    EEK
    -0.09
    holm
    -0.09
    POSITIVE LOGITS
    /us
    0.11
    åī¡
    0.10
    æ±īè¯Ń
    0.09
    à¹Ģà¸Ńà¸ĩ
    0.09
    èĩ³äºİ
    0.09
    -même
    0.09
     Benson
    0.08
    yr
    0.08
    ıs
    0.08
    athi
    0.08
    Activations Density 0.060%

    No Known Activations