© 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. 5084
    Prev
    Next
    INDEX
    Explanations

    Tufts, Tuamotu, Tuareg, Tuamie, TUPE, Tusculum

    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
    kur
    -0.09
    ç¾¤å²Ľ
    -0.09
    -sama
    -0.09
    Çİ
    -0.09
    çĺķ
    -0.08
    å½ĵä¹ĭ
    -0.08
     ninete
    -0.08
    _widgets
    -0.08
     squirt
    -0.08
    ãĤ£
    -0.08
    POSITIVE LOGITS
    ture
    0.12
    麽
    0.09
    ereal
    0.09
    éĨª
    0.09
    on
    0.09
    åĨ¤
    0.09
    acles
    0.09
    aneously
    0.09
    è¿ĩ硬
    0.09
    enge
    0.08
    Activations Density 0.013%

    No Known Activations