© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10414
    Prev
    Next
    INDEX
    Explanations

    ./electrum or similar executables

    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
    纵深
    -0.08
     Herbert
    -0.08
    溥
    -0.08
     полÑĮзÑĥ
    -0.08
    ors
    -0.08
    æį®è¯´
    -0.08
    Named
    -0.08
    case
    -0.08
    èµĽåIJİ
    -0.08
    åľ¨æ·±åľ³
    -0.07
    POSITIVE LOGITS
    æ¯ķç«Łæĺ¯
    0.10
    çĬ¶æĢģä¸ĭ
    0.09
    ienie
    0.09
    thora
    0.09
    æĥħåĨµä¸ĭ
    0.09
    çľĭå¾ħ
    0.09
    å°±æĦıåij³çĿĢ
    0.08
    æī°ä¹±
    0.08
    éĢŁåº¦å¿«
    0.08
    Advertisements
    0.08
    Activations Density 0.651%

    No Known Activations