© 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. 27470
    Prev
    Next
    INDEX
    Explanations

    unplug, uninstall, unselected

    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
    å¼ĢéĺĶ
    -0.09
    arn
    -0.09
    æĭľ
    -0.09
    强迫
    -0.08
    lect
    -0.08
    没åĬŀæ³ķ
    -0.08
    Ø®ÙĦÙģ
    -0.08
    åıĬåħ¶
    -0.08
    诫
    -0.08
    称ä¹ĭ
    -0.08
    POSITIVE LOGITS
    AKE
    0.10
    éĩįéĩį
    0.10
    .boost
    0.10
    ftime
    0.09
    ä¸įäºĨ
    0.09
    ftype
    0.09
    /disable
    0.09
    /comment
    0.09
    ONTAL
    0.09
    åİŁä¾Ĩ
    0.09
    Activations Density 0.029%

    No Known Activations