© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51097
    Prev
    Next
    INDEX
    Explanations

    services and records

    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
    è¦ģ害
    -0.10
    赶
    -0.10
    jer
    -0.09
    æĻĴ
    -0.09
    _GAP
    -0.08
     TS
    -0.08
    _executor
    -0.08
    å²©çŁ³
    -0.08
    è°¨
    -0.08
    gap
    -0.08
    POSITIVE LOGITS
    人åĬĽ
    0.11
    èĹ¿
    0.09
    æĤī
    0.09
    èĩªåĬ©
    0.09
    äºĮ代
    0.09
    ÑģÑģ
    0.09
     tre
    0.09
    æıIJèµ·
    0.09
    çłij
    0.09
     Cot
    0.08
    Activations Density 0.142%

    No Known Activations