© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21004
    Prev
    Next
    INDEX
    Explanations

    pride and its common follow-ups

    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
    tered
    -0.11
    åħĴ
    -0.10
    èĩªå¦Ĥ
    -0.10
    ä¸įä¸Ĭ
    -0.10
    ation
    -0.09
    åĦ¿
    -0.09
    logy
    -0.09
    roman
    -0.09
    OOD
    -0.09
    ivers
    -0.09
    POSITIVE LOGITS
    fully
    0.13
    ful
    0.12
    ably
    0.12
    ç͍æĪ·æıIJä¾Ľ
    0.11
    鬣
    0.11
    holders
    0.10
    untas
    0.09
    SELF
    0.09
    FUL
    0.09
    enburg
    0.09
    Activations Density 0.008%

    No Known Activations