© 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. 32304
    Prev
    Next
    INDEX
    Explanations

    -ized, -ised, -ize, -ise suffixes

    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
    íŀĪ
    -0.13
    ness
    -0.12
    iful
    -0.11
    lessly
    -0.10
    LESS
    -0.10
    ÑģÑĤвеннÑĭе
    -0.09
    wood
    -0.09
    thing
    -0.09
    è¡Įãģį
    -0.09
    -handed
    -0.09
    POSITIVE LOGITS
    íıIJ
    0.11
    0.11
    ema
    0.10
    rtl
    0.10
    ç¨ĭ度
    0.09
    mö
    0.09
    ebra
    0.09
    ally
    0.09
    ERO
    0.09
    浪潮
    0.09
    Activations Density 0.290%

    No Known Activations