© 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. 62866
    Prev
    Next
    INDEX
    Explanations

    ownership percentages

    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
    åľ©
    -0.10
    ä¸Ńç§ĭ
    -0.09
    eor
    -0.09
    Joined
    -0.08
    æī¹ç¤º
    -0.08
    _PREF
    -0.08
    rup
    -0.08
    æĪIJåIJį
    -0.08
    æĪ¿äº§
    -0.08
    pei
    -0.08
    POSITIVE LOGITS
    èĤ¡æĿĥ
    0.12
    æĮģèĤ¡
    0.11
    份é¢Ŀ
    0.11
    æݧèĤ¡
    0.11
    æĮģæľīçļĦ
    0.11
    æ¯Ķä¾ĭ
    0.11
    æĮģæľī
    0.11
    ä¸İåħ¶
    0.10
    æݧèĤ¡èĤ¡ä¸ľ
    0.10
    æĶ¶è´Ń
    0.10
    Activations Density 0.168%

    No Known Activations