© 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. 1327
    Prev
    Next
    INDEX
    Explanations

    place names ending in burg

    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
    peare
    -0.11
    ÑģÑı
    -0.11
    iated
    -0.10
    ÙĦع
    -0.10
    们
    -0.10
    ä¸į该
    -0.10
    _TV
    -0.10
    hip
    -0.10
    ç«Ļéķ¿
    -0.10
    hood
    -0.10
    POSITIVE LOGITS
    ers
    0.11
    ties
    0.09
    liest
    0.09
    t
    0.08
    ities
    0.08
    red
    0.08
    éĩĬ
    0.08
    anova
    0.08
    uers
    0.08
    rent
    0.08
    Activations Density 0.008%

    No Known Activations