© 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. 31719
    Prev
    Next
    INDEX
    Explanations

    time to make a

    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
    åīįä¸ī
    -0.09
    å¾Īå¿«
    -0.09
    çħ§æł·
    -0.08
    mere
    -0.08
    presso
    -0.08
    bole
    -0.08
     eventual
    -0.08
     pv
    -0.08
    æľ¯
    -0.08
     desire
    -0.08
    POSITIVE LOGITS
    äºĨ解ä¸Ģä¸ĭ
    0.13
    è°Īè°Ī
    0.12
    ä»ĭç»įä¸Ģä¸ĭ
    0.10
    è¿Ļä½į
    0.10
    วà¸ĩ
    0.10
    æĥ³æĥ³
    0.10
     дек
    0.09
    éĹ®éĹ®
    0.09
    ä¹Łå¼Ģå§ĭ
    0.09
    ä¸į论æĺ¯
    0.09
    Activations Density 0.046%

    No Known Activations