© 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. 4568
    Prev
    Next
    INDEX
    Explanations

    words and definitions

    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
     Flesh
    -0.10
    èĤ¤èī²
    -0.09
    .setTo
    -0.09
    alent
    -0.09
    å¦
    -0.09
     воп
    -0.08
    å®īå®ģ
    -0.08
    访è°Ī
    -0.08
     esl
    -0.08
    mates
    -0.08
    POSITIVE LOGITS
    äºĮåŃĹ
    0.23
    è¿Ļ个è¯į
    0.21
     words
    0.21
     word
    0.20
    åŃĹæł·
    0.19
     Ñģлов
    0.16
     Ñģлова
    0.16
    word
    0.16
    è¿Ļåı¥è¯Ŀ
    0.15
    -word
    0.15
    Activations Density 0.074%

    No Known Activations