© 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. 5312
    Prev
    Next
    INDEX
    Explanations

    monoclonal antibody

    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
    ä½İ碳
    -0.09
    èĸ°
    -0.09
    emo
    -0.08
    culo
    -0.08
    upy
    -0.08
    woo
    -0.08
    修补
    -0.08
    ional
    -0.08
    çĨı
    -0.08
    yre
    -0.08
    POSITIVE LOGITS
    æĬĹä½ĵ
    0.10
     antibodies
    0.10
    æĺ¯éĿŀ
    0.09
    ucky
    0.09
    çģ«åĬĽ
    0.09
    æµĬ
    0.09
    è§ĤéŁ³
    0.09
    é»ij马
    0.09
    iedades
    0.09
    çĥŃè¡Ģ
    0.09
    Activations Density 0.346%

    No Known Activations