© 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. 22707
    Prev
    Next
    INDEX
    Explanations

    United States alone

    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
    ITTER
    -0.10
    çļĦæĦŁè§ī
    -0.10
    èĥĮæĻ¯
    -0.10
    æĢĿ绪
    -0.09
    豫
    -0.09
    çķı
    -0.09
    åįģä¹Ŀå±Ĭ
    -0.09
    utra
    -0.09
    å±¥
    -0.09
    ç»İ
    -0.09
    POSITIVE LOGITS
     alone
    0.22
    alone
    0.21
    ãģłãģijãģ§
    0.16
     saja
    0.15
     Alone
    0.14
    èĢĮå·²
    0.13
    å°±æľī
    0.12
    åįķåįķ
    0.12
    ãģłãģij
    0.11
    -alone
    0.11
    Activations Density 0.080%

    No Known Activations