© 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. 38803
    Prev
    Next
    INDEX
    Explanations

    as they

    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
    éļĶ
    -0.11
    èĻ¹
    -0.10
    åı¯ä»¥è¯´
    -0.10
    éģ¿
    -0.09
    å²±
    -0.09
    çĸı
    -0.08
    çľĭå¾Ĺ
    -0.08
     PMC
    -0.08
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.08
    ovan
    -0.08
    POSITIVE LOGITS
    éļıçĿĢ
    0.12
    éļ¨èijĹ
    0.10
    å¥¹åľ¨
    0.10
    ìĸij
    0.10
    æīĵéĢłåĩº
    0.10
    æįį
    0.09
    ä»Ķç»Ĩ
    0.09
    沿çĿĢ
    0.09
    ä½łåľ¨
    0.09
    æŃ¤äºº
    0.09
    Activations Density 0.066%

    No Known Activations