© 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. 6986
    Prev
    Next
    INDEX
    Explanations

    light or right

    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
    ption
    -0.11
    ä¸įä¸Ĭ
    -0.11
    oftware
    -0.10
    缴è¾ĸå¸Ĥ
    -0.10
    iento
    -0.09
    ftware
    -0.09
    说æĺ¯
    -0.09
    ../
    -0.09
    IJ
    -0.09
    highlight
    -0.09
    POSITIVE LOGITS
    ened
    0.16
    ening
    0.16
    ãģĹãģ¾ãģĨ
    0.16
    fully
    0.16
    est
    0.14
    mare
    0.13
    ê¹Ķ
    0.12
    -hearted
    0.11
    ãģĹãģ¾
    0.11
    edly
    0.11
    Activations Density 0.069%

    No Known Activations