© 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. 3895
    Prev
    Next
    INDEX
    Explanations

    inductance, capacitance, impedance

    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
    ä¸įåĩºæĿ¥
    -0.09
    éĹ°
    -0.09
    æĿª
    -0.09
    æģ¯
    -0.09
    apers
    -0.08
     ÑĥвеÑĢ
    -0.08
    ads
    -0.08
    踩
    -0.08
    å¸ĺ
    -0.08
    è¶Ł
    -0.08
    POSITIVE LOGITS
    ä¸Ŀä¸Ŀ
    0.11
    çµ²
    0.11
    çĴŀ
    0.10
    åĽ¢éķ¿
    0.10
    串èģĶ
    0.10
    ä¸Ŀ
    0.10
    æĹłç©·
    0.08
    åĽ¢åijĺ
    0.08
    åĽ¢
    0.08
    æĪIJåĪĨ
    0.08
    Activations Density 0.104%

    No Known Activations