© 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. 11218
    Prev
    Next
    INDEX
    Explanations

    as-is disclaimer

    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
    éŃĤ
    -0.10
    _formatter
    -0.09
    åħ´å¥ĭ
    -0.08
    imb
    -0.08
    罡
    -0.08
    ãĥIJãĥ¬
    -0.08
    nip
    -0.08
    IPLE
    -0.08
    æĥĬèī³
    -0.08
    ãĤĴåıĸãĤĬ
    -0.08
    POSITIVE LOGITS
    ãģĿãģ®ãģ¾ãģ¾
    0.16
    çİ°çĬ¶
    0.15
    ãģ¾ãģ¾
    0.14
    çİ°æľīçļĦ
    0.13
    çļĦæł·åŃIJ
    0.12
    çİ°æľī
    0.12
    çļĦæ¨¡æł·
    0.12
    æł·åŃIJ
    0.11
    çĬ¶æĢģä¸ĭ
    0.10
    æ¨¡æł·
    0.10
    Activations Density 0.087%

    No Known Activations