© 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. 8840
    Prev
    Next
    INDEX
    Explanations

    will or capitalised Will

    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
    ello
    -0.11
    ega
    -0.10
    uring
    -0.10
    æ¿ĢçĥĪ
    -0.10
    emia
    -0.10
    edition
    -0.10
    iddle
    -0.10
    ally
    -0.09
    illion
    -0.09
    iled
    -0.09
    POSITIVE LOGITS
    fully
    0.14
    iams
    0.13
    istic
    0.10
    power
    0.10
    l
    0.09
     ÑıвлÑı
    0.09
    ibr
    0.09
    kommen
    0.09
    owy
    0.09
    ful
    0.09
    Activations Density 0.041%

    No Known Activations