© 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. 50911
    Prev
    Next
    INDEX
    Explanations

    words starting with W

    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
    /write
    -0.12
    wave
    -0.11
    å¨ĥ
    -0.10
    western
    -0.10
    åºľ
    -0.10
    ially
    -0.10
    wahl
    -0.09
     волн
    -0.09
    umer
    -0.09
    illion
    -0.09
    POSITIVE LOGITS
    robe
    0.14
    fully
    0.14
    ylie
    0.13
    ritable
    0.12
    itten
    0.12
    nesday
    0.12
    consin
    0.12
    ELCOME
    0.12
    melon
    0.12
    raith
    0.12
    Activations Density 0.983%

    No Known Activations