© 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. 61506
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions

    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
    对å¤ĸ
    -0.09
    åĩī
    -0.09
    retty
    -0.09
    ä¼´éļı
    -0.09
    åĴ
    -0.09
    èµ°åĪ°
    -0.08
    gon
    -0.08
    ãģ«ãģªãĤĭãģ¨
    -0.08
    æĮ£
    -0.08
    è·Łéļı
    -0.08
    POSITIVE LOGITS
    ellas
    0.11
    /legal
    0.09
    éĤ£éĩĮ
    0.09
     они
    0.09
    uter
    0.09
    æѤäºĭ
    0.09
    utan
    0.08
    uta
    0.08
    Ю
    0.08
    åĢŁè´·
    0.08
    Activations Density 0.095%

    No Known Activations