© 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. 56953
    Prev
    Next
    INDEX
    Explanations

    tools and weapons

    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
    uset
    -0.10
    æľºåĻ¨
    -0.10
    禽
    -0.09
    åħĭæľį
    -0.09
    计ç®ĹåĻ¨
    -0.09
     Rol
    -0.09
    ournal
    -0.09
     beast
    -0.09
    itch
    -0.09
    大大å°ı
    -0.08
    POSITIVE LOGITS
    æĺ¯çĶ¨æĿ¥
    0.12
    æŁĦ
    0.12
    æĭ¿åĩºæĿ¥
    0.11
    æĭ¿æĿ¥
    0.11
    åıĬ缸åħ³
    0.10
    æ³Ĺ
    0.10
     used
    0.09
    ç¢İçīĩ
    0.09
     Used
    0.09
    ãĤĴæĮģãģ£ãģ¦
    0.09
    Activations Density 0.074%

    No Known Activations