© 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. 60963
    Prev
    Next
    INDEX
    Explanations

    violating rules or laws

    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
    èµĽ
    -0.10
    å¥¥åľ°
    -0.09
     Wash
    -0.09
    .getvalue
    -0.08
    _DISP
    -0.08
    okin
    -0.08
     Cards
    -0.08
    _sz
    -0.08
    erta
    -0.08
    orb
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.11
    æļĹ示
    0.11
    æĥħå½¢
    0.10
     or
    0.10
    严éĩįå½±åĵį
    0.10
    åij¼åĶ¤
    0.10
    idge
    0.09
    íķĺê±°ëĤĺ
    0.09
    çļĦæĥħå½¢
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    Activations Density 0.028%

    No Known Activations