© 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. 56378
    Prev
    Next
    INDEX
    Explanations

    why not followed by verb

    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
    ival
    -0.10
    è¿ĺè®°å¾Ĺ
    -0.10
    alte
    -0.10
    人次
    -0.10
    oris
    -0.10
    argo
    -0.10
    æ¯Ķå¦Ĥ说
    -0.09
    åı©
    -0.09
    é¾ĻéŨ
    -0.09
     ׾×ŀש׾
    -0.09
    POSITIVE LOGITS
    åķ¬
    0.09
    raries
    0.09
    _gener
    0.09
    为ä¹ĭ
    0.09
    æĭ©
    0.09
     Rena
    0.08
    éģĤ
    0.08
     others
    0.08
     Deb
    0.08
    ongs
    0.08
    Activations Density 0.008%

    No Known Activations