© 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. 11091
    Prev
    Next
    INDEX
    Explanations

    states of mind

    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
    éĺ±
    -0.11
    温æļĸ
    -0.11
    ä½ľåĩºäºĨ
    -0.10
    è°¦
    -0.10
    ãĥIJãĥĥãĤ¯
    -0.10
    éĢłæĪIJäºĨ
    -0.10
    åİĮæģ¶
    -0.10
    çĤķ
    -0.09
    èĥ½çľĭåĩº
    -0.09
    å»īæ´ģ
    -0.09
    POSITIVE LOGITS
    æģį
    0.11
    æĥļ
    0.11
     trance
    0.11
    çĬ¶æĢģä¸ĭ
    0.11
    çĬ¶æĢģ
    0.11
    çĹ´
    0.10
    è¿·
    0.10
    num
    0.09
     state
    0.09
    éº»æľ¨
    0.09
    Activations Density 0.170%

    No Known Activations