© 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. 10021
    Prev
    Next
    INDEX
    Explanations

    throw with prepositions/adverbs

    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
    ually
    -0.13
    æŶåĢĻ
    -0.11
    uality
    -0.11
    urator
    -0.10
    urve
    -0.10
    人士
    -0.10
    urate
    -0.09
    ¡
    -0.09
    黥
    -0.09
    uele
    -0.08
    POSITIVE LOGITS
    aways
    0.14
    away
    0.13
    backs
    0.11
    er
    0.11
    abouts
    0.10
    outs
    0.10
    -away
    0.09
    outed
    0.09
    lish
    0.09
    ¥
    0.09
    Activations Density 0.018%

    No Known Activations