© 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. 57388
    Prev
    Next
    INDEX
    Explanations

    the only downside is

    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
    çļĦä¸ĢåĪĩ
    -0.11
    æľīå¾Īå¤ļç§į
    -0.09
    å·²ä¹ħ
    -0.09
    æľī两ç§į
    -0.09
     Heard
    -0.09
    inger
    -0.09
     zwar
    -0.09
    .getError
    -0.09
    äºĮ次
    -0.09
    heimer
    -0.08
    POSITIVE LOGITS
     tomb
    0.09
    iscard
    0.09
    åı¯æĥľ
    0.09
    æĬĢæľ¯çłĶåıij
    0.09
     hơi
    0.09
    edar
    0.09
    etter
    0.09
    Diamond
    0.08
    iband
    0.08
    andel
    0.08
    Activations Density 0.023%

    No Known Activations