© 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. 8702
    Prev
    Next
    INDEX
    Explanations

    good condition

    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
     доÑģÑĤиж
    -0.10
    æĢ§å¼º
    -0.09
    åĽ½æ°ijåħļ
    -0.08
    è§īå¾Ĺèĩªå·±
    -0.08
    itivity
    -0.08
    åĢľ
    -0.08
    Verse
    -0.08
    æ²ī
    -0.08
    illos
    -0.08
    ä¹ĭåĬĽ
    -0.08
    POSITIVE LOGITS
    olib
    0.10
    wed
    0.10
    bben
    0.10
    awan
    0.10
    FUL
    0.09
    ward
    0.09
    bilt
    0.09
    лив
    0.08
    ãĦĴ
    0.08
    омеÑĢ
    0.08
    Activations Density 0.014%

    No Known Activations