© 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. 10650
    Prev
    Next
    INDEX
    Explanations

    thoughts and thinking

    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
    æĬł
    -0.09
    vang
    -0.09
    线ä¸Ĭ
    -0.09
    ember
    -0.09
    åİļ度
    -0.08
    _LESS
    -0.08
    è§Į
    -0.08
     вÑģего
    -0.08
    éħ¥
    -0.08
    _testing
    -0.08
    POSITIVE LOGITS
     thoughts
    0.19
    念头
    0.18
     Thoughts
    0.17
    æĥ³åĪ°
    0.14
    thought
    0.13
    Thought
    0.12
    çļĦæĥ³æ³ķ
    0.12
    æĥ³æ³ķ
    0.12
    èĦijåŃIJéĩĮ
    0.11
    æĥ³çĿĢ
    0.11
    Activations Density 0.065%

    No Known Activations