© 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. 58239
    Prev
    Next
    INDEX
    Explanations

    words starting with Ta

    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
    ç¬Ĩ
    -0.11
    ãģĹãģ¾ãģĨ
    -0.11
    ìį¨
    -0.10
    sek
    -0.09
    erton
    -0.09
    tures
    -0.09
    裳
    -0.09
    OrElse
    -0.09
     Seah
    -0.09
    secutive
    -0.09
    POSITIVE LOGITS
    ãģ£ãģĵ
    0.09
    ities
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    cade
    0.08
    åĽŀäºĭ
    0.08
    ucks
    0.08
    ucc
    0.08
    们çļĦ
    0.08
    ãģ¹ãģį
    0.08
    erk
    0.08
    Activations Density 0.036%

    No Known Activations