© 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. 22832
    Prev
    Next
    INDEX
    Explanations

    classification, nuclei, Big Air, 'Antoni

    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
    hel
    -0.10
     باÙĦت
    -0.09
    æį¢äºĨ
    -0.09
    edly
    -0.08
    ä¸ĩåı°
    -0.08
    Hel
    -0.08
    isplay
    -0.08
    داء
    -0.08
    ubb
    -0.08
    atform
    -0.08
    POSITIVE LOGITS
    躺çĿĢ
    0.08
    czy
    0.08
    çĥŁçģ«
    0.08
    èµŃ
    0.08
    Criteria
    0.08
    uml
    0.08
    éĵ²
    0.08
    round
    0.08
    éºĴ
    0.08
    ä¸ĵ家
    0.08
    Activations Density 0.026%

    No Known Activations