© 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. 5249
    Prev
    Next
    INDEX
    Explanations

    screening

    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
    带头
    -0.10
    çīµæīĭ
    -0.10
    ofil
    -0.09
    ofs
    -0.09
    cul
    -0.09
    ume
    -0.09
    åĬª
    -0.09
     Antar
    -0.09
    ofi
    -0.09
    æĻ¦
    -0.08
    POSITIVE LOGITS
    çŃĽ
    0.11
    .Screen
    0.10
    çŃĽéĢī
    0.10
    çĶĦ
    0.10
     screening
    0.10
    bounding
    0.09
    ä¸Ģçľ¼
    0.09
    æĴ°åĨĻ
    0.09
    çªģåĩºéĹ®é¢ĺ
    0.09
    è§ĨåIJ¬
    0.09
    Activations Density 0.055%

    No Known Activations