© 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. 31995
    Prev
    Next
    INDEX
    Explanations

    short story or stories

    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
    åĶ±çīĩ
    -0.10
    æĸ¹åľĨ
    -0.10
    æ»Ķ
    -0.09
    åħ«åŃĹ
    -0.09
    OPY
    -0.09
    岩
    -0.08
    ossa
    -0.08
     Pry
    -0.08
    batim
    -0.08
    [arr
    -0.08
    POSITIVE LOGITS
    stories
    0.11
    æķħäºĭ
    0.11
     tales
    0.11
     stories
    0.11
     Stories
    0.10
    ä¸ĢåĪĻ
    0.10
    Stories
    0.10
    wives
    0.10
    èİ·å¥ĸ
    0.09
    -story
    0.09
    Activations Density 0.070%

    No Known Activations