© 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. 10711
    Prev
    Next
    INDEX
    Explanations

    quiet / silent 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
     Evel
    -0.09
    é¢ł
    -0.09
    æĸ¹æīį
    -0.09
    ãģĦãģĭ
    -0.08
     Ñģм
    -0.08
     tal
    -0.08
    eneg
    -0.08
    éģĹ
    -0.07
    ected
    -0.07
    åħ´å¥ĭ
    -0.07
    POSITIVE LOGITS
    é»ĺé»ĺ
    0.24
    æĹłå£°
    0.23
    é»ĺé»ĺåľ°
    0.21
    é»ĺ
    0.21
    éĿĻéĿĻ
    0.18
    éĿĻéĿĻåľ°
    0.17
    éĿĻ
    0.17
    åĵij
    0.16
    å®īéĿĻ
    0.16
    æ²īé»ĺ
    0.16
    Activations Density 0.057%

    No Known Activations