© 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. 4787
    Prev
    Next
    INDEX
    Explanations

    tells 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
    çĪª
    -0.10
     Pier
    -0.09
    DER
    -0.08
    èĪĮ
    -0.08
     ju
    -0.08
    èĮ«èĮ«
    -0.08
    deo
    -0.08
    æĪij个人
    -0.08
     Claw
    -0.08
    ä¸ĢåĿĹ
    -0.08
    POSITIVE LOGITS
    æķħäºĭ
    0.12
    çļĦæķħäºĭ
    0.11
    ç¬ijè¯Ŀ
    0.11
     stories
    0.10
     Stories
    0.10
    åħ¨éĿ¢
    0.10
     STORY
    0.10
    stories
    0.10
    Story
    0.10
    /story
    0.10
    Activations Density 0.060%

    No Known Activations