© 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. 62574
    Prev
    Next
    INDEX
    Explanations

    no problem

    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¸įå¾Ĺå·²
    -0.12
    åºĨ幸
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    æĹłå¥Ī
    -0.09
    ä»Ģä¹Īæł·
    -0.09
    æĩĤå¾Ĺ
    -0.08
    ä¸įå¾Ĺ
    -0.08
    ugu
    -0.08
    æĥħ趣
    -0.08
    allo
    -0.08
    POSITIVE LOGITS
    CHA
    0.09
    ERO
    0.09
    Bur
    0.09
    .IsNullOr
    0.09
     bur
    0.09
    bur
    0.09
    ungs
    0.09
    PasswordEncoder
    0.09
     whatsoever
    0.09
    æľīä»»ä½ķ
    0.09
    Activations Density 0.024%

    No Known Activations