© 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. 19530
    Prev
    Next
    INDEX
    Explanations

    cross followed by word

    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
    asto
    -0.10
    çĿ¬
    -0.10
    utan
    -0.10
    å©¿
    -0.10
    ishment
    -0.09
    arker
    -0.09
    arket
    -0.09
    oir
    -0.09
    ush
    -0.09
    vers
    -0.09
    POSITIVE LOGITS
    ible
    0.11
    ed
    0.11
    ses
    0.10
    most
    0.10
    able
    0.10
    sed
    0.10
    ingly
    0.09
    tures
    0.09
    ings
    0.09
    berry
    0.09
    Activations Density 0.046%

    No Known Activations