© 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. 18075
    Prev
    Next
    INDEX
    Explanations

    switch on or off

    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
    纽
    -0.09
    ç¼ī
    -0.09
    5
    -0.09
    2
    -0.09
    åĵģ
    -0.09
    6
    -0.08
    8
    -0.08
    ucas
    -0.08
    7
    -0.08
    Popular
    -0.08
    POSITIVE LOGITS
     off
    0.12
    OFF
    0.10
     OFF
    0.10
    -off
    0.10
    åıī
    0.10
    ä¸ĢéĿ¢
    0.09
    Off
    0.09
    çŁ¥æĻĵ
    0.09
    _off
    0.09
    dns
    0.09
    Activations Density 0.041%

    No Known Activations