© 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. 35302
    Prev
    Next
    INDEX
    Explanations

    disprove, refute, rebut, wrong

    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
    åĨ°éĽª
    -0.09
    assel
    -0.09
    istar
    -0.09
    ens
    -0.08
    å¼Ģè¾Ł
    -0.08
    .dirty
    -0.08
    جاز
    -0.08
    ENS
    -0.08
     vero
    -0.08
    shaw
    -0.08
    POSITIVE LOGITS
    ç½Ħ
    0.10
    ildo
    0.09
    奶ç²ī
    0.09
    åijĶ
    0.09
     Weston
    0.09
    å»ĵ
    0.09
     hood
    0.09
    社ä¼ļç§ijåѦ
    0.08
    èı½
    0.08
    æ®Ħ
    0.08
    Activations Density 0.009%

    No Known Activations