© 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. 49335
    Prev
    Next
    INDEX
    Explanations

    under conditions

    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
    DECL
    -0.13
    cket
    -0.10
    æ¢ĥ
    -0.10
    è°¨
    -0.09
    èIJ¼
    -0.09
    ç²¾çĽĬæ±Ĥç²¾
    -0.09
    atro
    -0.09
    HTML
    -0.09
    ç»ıéªĮåĢ¼
    -0.09
    礼æĭľ
    -0.09
    POSITIVE LOGITS
    åħ·ä½ĵæĥħåĨµ
    0.10
    ä½İåİĭ
    0.09
    çļĦåĬ¨åĬĽ
    0.09
    åĪºæ¿Ģ
    0.09
    assen
    0.09
    ivable
    0.09
    upert
    0.09
    echa
    0.09
    ivor
    0.08
    .stamp
    0.08
    Activations Density 0.225%

    No Known Activations