© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38360
    Prev
    Next
    INDEX
    Explanations

    first to achieve or begin something

    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
    istani
    -0.10
    HELL
    -0.09
    enha
    -0.09
    зам
    -0.09
    lated
    -0.09
    åĬłåĪĨ
    -0.09
    hazi
    -0.09
    pez
    -0.09
    MMdd
    -0.09
    æ»ŀåIJİ
    -0.09
    POSITIVE LOGITS
    å¦ĤæѤ
    0.09
    çŃ¾åŃĹ
    0.08
     actually
    0.08
    å¾Ĺèµ·
    0.08
    ART
    0.08
    ç¬Ķ
    0.08
     exploits
    0.07
     EVER
    0.07
    outer
    0.07
     so
    0.07
    Activations Density 0.053%

    No Known Activations