© 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. 32215
    Prev
    Next
    INDEX
    Explanations

    deemed + adjective/noun

    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
    à¨Ĩ
    -0.10
    Ñĩки
    -0.10
    ç¼®
    -0.10
    ŀ
    -0.09
    esco
    -0.09
    æĺİåªļ
    -0.09
    дей
    -0.09
    -minded
    -0.09
    rop
    -0.09
    ESCO
    -0.09
    POSITIVE LOGITS
    phas
    0.14
    cene
    0.11
    ably
    0.11
    lessly
    0.11
    ings
    0.10
    å¸ĺ
    0.09
    åŃ½
    0.09
    æĽĻ
    0.08
    edException
    0.08
    ems
    0.08
    Activations Density 0.007%

    No Known Activations