© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8546
    Prev
    Next
    INDEX
    Explanations

    boil, boiled, boiling

    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
    uele
    -0.09
    iveness
    -0.08
    presso
    -0.08
    apos
    -0.08
    宪æ³ķ
    -0.08
    stab
    -0.08
    ially
    -0.08
    re
    -0.08
    .ra
    -0.08
    akit
    -0.08
    POSITIVE LOGITS
    strap
    0.11
    å¤ļå¹´çļĦ
    0.10
    è¡·
    0.09
    ìį¨
    0.09
    éĿŀåĩ¡
    0.09
    å±ij
    0.09
    è¿Ļä¸Ģå¹´
    0.09
    ÑģÑı
    0.09
    shed
    0.09
    åĩºè®©
    0.09
    Activations Density 0.017%

    No Known Activations