© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    what comes next

    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
    åºľ
    -0.09
    ä¸Ģ次
    -0.09
    æŶéļĶ
    -0.09
    ify
    -0.08
    èijµ
    -0.08
    fm
    -0.07
    åĽĽå¹´
    -0.07
    â
    -0.07
    詳
    -0.07
    1
    -0.07
    POSITIVE LOGITS
    _mgmt
    0.11
    anson
    0.11
    loat
    0.10
    诣
    0.09
    .Pointer
    0.09
    _icall
    0.09
    IGH
    0.09
    çIJ¬
    0.09
    好çİ©
    0.09
    æĪij说
    0.09
    Activations Density 0.045%

    No Known Activations