© 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. 31794
    Prev
    Next
    INDEX
    Explanations

    specific sentence beginnings

    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
    æĿª
    -0.10
    ä¸Ģæ³¢
    -0.09
    æħij
    -0.08
    EObject
    -0.08
    å¤ĩ
    -0.08
    UME
    -0.08
    çļĦä¸ĢéĿ¢
    -0.08
    ä¸Ģæīĭ
    -0.08
    çķĻè¨ĢæĿ¿
    -0.08
    潦
    -0.08
    POSITIVE LOGITS
    æĥ³çŁ¥éģĵ
    0.08
    æīįèĥ½å¤Ł
    0.08
    èĸ°
    0.08
     dus
    0.08
    ardy
    0.08
    èĦĤèĤª
    0.08
    æķħäºĭ
    0.08
    座
    0.08
    ANTE
    0.07
    odu
    0.07
    Activations Density 0.326%

    No Known Activations