© 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. 22659
    Prev
    Next
    INDEX
    Explanations

    top of page or document

    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
    ambre
    -0.09
    inish
    -0.08
    erm
    -0.08
    rag
    -0.08
    ownt
    -0.08
    æ²£
    -0.08
     Boss
    -0.08
    åŁĭ
    -0.08
     rag
    -0.08
    åĴ¬
    -0.08
    POSITIVE LOGITS
    (top
    0.09
    èĻı
    0.09
    top
    0.09
    é«
    0.09
    [top
    0.09
    header
    0.09
    _ATOM
    0.09
    ä¸įæĦ¿
    0.09
    iren
    0.08
    èĺijèıĩ
    0.08
    Activations Density 0.047%

    No Known Activations