© 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. 19271
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    èĤ¤èī²
    -0.13
    ç§įæĹı
    -0.12
    èĪľ
    -0.11
     race
    -0.10
     Race
    -0.10
    race
    -0.10
    æľīèī²
    -0.10
    çĥ«
    -0.10
     racial
    -0.10
    Race
    -0.10
    POSITIVE LOGITS
     INLINE
    0.09
    æ§ĥ
    0.09
    uary
    0.08
    annes
    0.08
    å§Ķå±Ī
    0.08
    éĿ©æĸ°
    0.08
    ãģªãģĦãĤĪãģĨãģ«
    0.08
    ä¸ĢéŨ
    0.08
    ilities
    0.08
    ç²¾ç¥ŀ
    0.08
    Activations Density 0.092%

    No Known Activations