© 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. 1159
    Prev
    Next
    INDEX
    Explanations

    starts/ends phrases with authors/decimal

    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
    éĻ·åħ¥
    -0.09
    rug
    -0.08
    è¿IJè´¹
    -0.08
    {:
    -0.08
     strokes
    -0.08
    ä¹ĭ家
    -0.08
     texas
    -0.08
    çł´
    -0.08
    羣è¯ļ
    -0.08
    ÑĤÑıж
    -0.08
    POSITIVE LOGITS
    ãĤĴæĦŁãģĺ
    0.10
    èµĽåIJİ
    0.10
    ä¸ĢçĤ¹çĤ¹
    0.10
    æĦ
    0.10
    ANCEL
    0.10
    æĦŁåıĹ
    0.09
    äºij端
    0.09
    å¤įæŁ¥
    0.09
    è¿Ľå±ķæĥħåĨµ
    0.09
    涿
    0.09
    Activations Density 0.019%

    No Known Activations