© 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. 50048
    Prev
    Next
    INDEX
    Explanations

    wounded, missing, or dead people

    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
    éĦĻ
    -0.09
    æķĻæ¡Ī
    -0.09
    说çĿĢ
    -0.09
    çĤ·
    -0.09
    uki
    -0.09
    椴
    -0.09
    éħ¿éĢł
    -0.09
     Philips
    -0.08
    亲å¯Ĩ
    -0.08
    çľĭæĿ¥
    -0.08
    POSITIVE LOGITS
    èµ
    0.10
    èĪĴéĢĤçļĦ
    0.09
    äng
    0.08
    .paint
    0.08
     sạn
    0.08
     дог
    0.08
    è¯ľ
    0.08
    ulous
    0.08
     Wid
    0.08
    寡
    0.08
    Activations Density 0.022%

    No Known Activations