© 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. 11227
    Prev
    Next
    INDEX
    Explanations

    you followed by auxiliary/common verbs

    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
    CAPE
    -0.10
    allon
    -0.09
    æķĻä½ł
    -0.09
    çļĦæł¹æľ¬
    -0.09
    adia
    -0.09
    æīĢæīĢ
    -0.09
    è·³è·ĥ
    -0.09
    ommen
    -0.09
     eg
    -0.09
    çµĤ
    -0.08
    POSITIVE LOGITS
    æĬŁ
    0.09
    èĤ¤
    0.08
    æķ¦
    0.08
    毡
    0.08
    jom
    0.07
    isting
    0.07
    æĬ¡
    0.07
    ön
    0.07
    ä¸įåIJĮæĦı
    0.07
    ots
    0.07
    Activations Density 0.036%

    No Known Activations