© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57876
    Prev
    Next
    INDEX
    Explanations

    negative adjective completions

    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
    ä¾ij
    -0.10
    manship
    -0.10
    人士
    -0.10
    ÑĢей
    -0.09
    aroo
    -0.09
     Welch
    -0.09
    orld
    -0.09
     пÑĢин
    -0.08
    iverse
    -0.08
    ï¸ı
    -0.08
    POSITIVE LOGITS
    主æĦı
    0.12
    ãĤĤãģ®ãĤĴ
    0.10
    ities
    0.10
    çļĦäºĭæĥħ
    0.09
    -looking
    0.09
    ITY
    0.09
    housing
    0.09
    åѤç«ĭ
    0.09
    tics
    0.09
    .gdx
    0.09
    Activations Density 0.010%

    No Known Activations