© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53177
    Prev
    Next
    INDEX
    Explanations

    airfoil, coefficient, pitch, span, fin

    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
    ç«ĻçĿĢ
    -0.10
    ä¸ĢæŶ
    -0.09
    æĭīæĸ¯
    -0.09
    otyp
    -0.09
    èĤļ
    -0.09
    çĭĤ欢
    -0.09
    éĺľ
    -0.09
    çľĭçĶµå½±
    -0.09
    ĥģ
    -0.09
    ç¾Ĭæ¯Ľ
    -0.09
    POSITIVE LOGITS
    ãĤ¹ãĥĿ
    0.08
    稷
    0.08
     replicas
    0.08
    触åıij
    0.08
    å·¡åĽŀ
    0.07
    æµģçķħ
    0.07
     opendir
    0.07
    à¸Ħà¸Ń
    0.07
    åĨłåĨĽ
    0.07
    =D
    0.07
    Activations Density 0.057%

    No Known Activations