© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52066
    Prev
    Next
    INDEX
    Explanations

    Thorn and Horn names/places

    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
    ively
    -0.11
    ency
    -0.11
    ori
    -0.10
    operand
    -0.09
    HING
    -0.09
    ãģĤãģ£ãģ¦
    -0.09
    -minded
    -0.09
    ncy
    -0.09
    ucha
    -0.09
    uration
    -0.09
    POSITIVE LOGITS
    åľ°å¸¦
    0.10
    idon
    0.10
    NING
    0.10
    less
    0.10
    illos
    0.09
    çŀŃ
    0.09
    labs
    0.09
    Ñİ
    0.09
    uckle
    0.09
    veau
    0.09
    Activations Density 0.041%

    No Known Activations