© 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. 48954
    Prev
    Next
    INDEX
    Explanations

    car years and models

    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
    æĺİæľĹ
    -0.09
    orget
    -0.09
    èĥİ
    -0.09
    毡
    -0.09
    æ°Ķæ°Ľ
    -0.08
    ä¸ĢæīĢ
    -0.08
    鸡汤
    -0.08
    ä¸Ńå¼ı
    -0.08
     Tenn
    -0.08
    asy
    -0.08
    POSITIVE LOGITS
    严åİīæīĵåĩ»
    0.10
    ä¸įæĺİ
    0.10
    ged
    0.09
    unch
    0.09
    -year
    0.09
    æħij
    0.09
    æĶ¹è¿Ľ
    0.09
    çı
    0.09
    严åİī
    0.09
    åIJ¯çĶ¨
    0.08
    Activations Density 0.028%

    No Known Activations