© 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. 5905
    Prev
    Next
    INDEX
    Explanations

    commercially available

    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
    èįīåĿª
    -0.10
    pec
    -0.09
    ä»ĭ
    -0.09
    çł£
    -0.09
    æĦī
    -0.08
    éĴ¿
    -0.08
    主é¢ĺæ´»åĬ¨
    -0.08
    PEC
    -0.08
    eut
    -0.08
    æijĩ
    -0.08
    POSITIVE LOGITS
    å¸ĤéĿ¢ä¸Ĭ
    0.18
    å¸Ĥåľºä¸Ĭ
    0.17
    ä¹°åĪ°
    0.15
    ä¹°çļĦ
    0.13
    ä¹°
    0.13
    èĩªè¡Į
    0.13
    åľ¨å¸Ĥåľºä¸Ĭ
    0.12
    è´Ńä¹°
    0.11
    è²·
    0.11
     bought
    0.11
    Activations Density 0.223%

    No Known Activations