© 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. 17558
    Prev
    Next
    INDEX
    Explanations

    transportation funding and legislation

    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
    æĶ¾å¼Ģ
    -0.10
    æ¼Ĥæµģ
    -0.09
    æµģç¨ĭ
    -0.08
    Dock
    -0.08
    ä½į
    -0.08
    angkan
    -0.08
    çĨĶ
    -0.08
     Umb
    -0.08
    度è¿ĩ
    -0.08
    æµ·å°Ķ
    -0.08
    POSITIVE LOGITS
    åħ¬è·¯
    0.13
    è·¯åĨµ
    0.13
    éĢļ车
    0.12
    交éĢļå®īåħ¨
    0.12
    交éĢļ
    0.12
    è·¯éĿ¢
    0.11
    åħ»æĬ¤
    0.11
    é«ĺéĢŁåħ¬è·¯
    0.11
    æ²¥éĿĴ
    0.11
     Passenger
    0.10
    Activations Density 0.108%

    No Known Activations