© 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. 2882
    Prev
    Next
    INDEX
    Explanations

    pronouns (you, me, us, myself)

    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
    伸åĩº
    -0.10
    ç»İ
    -0.10
    rint
    -0.09
    æĭ¿èµ·
    -0.09
    iens
    -0.09
     breakdown
    -0.08
    åĬłçĽĸ
    -0.08
    GRADE
    -0.08
    beit
    -0.08
    _INCREMENT
    -0.08
    POSITIVE LOGITS
    çļĦæĥħ绪
    0.11
    éĢĦ
    0.10
    è¯ķçĤ¹å·¥ä½ľ
    0.10
    çļĦä¸Ģ大
    0.10
    çļĦä¸ĢéĿ¢
    0.10
    èĽŁ
    0.10
    çļĦ人çī©
    0.09
    çļĦæĥħæĦŁ
    0.09
    åľ¨è¿Ļ
    0.09
    çĻ¿
    0.09
    Activations Density 0.075%

    No Known Activations