© 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. 34540
    Prev
    Next
    INDEX
    Explanations

    Scripps, iHeart, Oath, Press

    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
    .gdx
    -0.10
    å°ĸåı«
    -0.09
     gü
    -0.09
    çªĴ
    -0.09
    ä¹ħ
    -0.09
    åĨĽå®ĺ
    -0.08
    寸
    -0.08
    atak
    -0.08
    éķ¿çĽ¸
    -0.08
    xia
    -0.08
    POSITIVE LOGITS
    ght
    0.09
    hek
    0.09
    رÙħ
    0.09
    çķĻç»Ļ
    0.08
    ality
    0.08
     Sheffield
    0.08
    çŃ¹
    0.08
    åĪ¤æĸŃ
    0.08
    inati
    0.08
    chet
    0.08
    Activations Density 0.020%

    No Known Activations