© 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. 33127
    Prev
    Next
    INDEX
    Explanations

    do not perform actions

    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
    åijĬè¯ī她
    -0.09
     phúc
    -0.09
    æľĭåıĭ们对
    -0.09
    _heads
    -0.09
    åıĮçľ¼
    -0.09
    çĤ¹çĤ¹å¤´
    -0.09
    è§īæĤŁ
    -0.09
    _compat
    -0.08
    igy
    -0.08
    buzz
    -0.08
    POSITIVE LOGITS
    èĩ´åĬĽ
    0.10
    ä¸įçķĻ
    0.10
    å®ŀè¡Į
    0.09
    ä¸įåħģ许
    0.09
     пÑĢакÑĤи
    0.09
    åıį对
    0.09
    Pes
    0.08
    ä»İæĿ¥ä¸į
    0.08
     typically
    0.08
     pes
    0.08
    Activations Density 0.041%

    No Known Activations