© 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. 49345
    Prev
    Next
    INDEX
    Explanations

    web site services

    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
    æĪijçĽ¸ä¿¡
    -0.10
    åIJĦè¡Į
    -0.09
    vu
    -0.09
    ç«Ł
    -0.08
    manage
    -0.08
    ekyll
    -0.08
     Vu
    -0.08
    ä¹ĺåĿIJ
    -0.07
    件
    -0.07
    åĽĽåij¨
    -0.07
    POSITIVE LOGITS
    legen
    0.10
    åį¤
    0.10
     Mast
    0.09
    综åIJĪåĪ©çĶ¨
    0.09
    _BUF
    0.09
    诸èijĽ
    0.09
    å²IJ
    0.09
    McC
    0.09
    好æľĭåıĭ
    0.09
    bum
    0.09
    Activations Density 0.006%

    No Known Activations