© 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. 38733
    Prev
    Next
    INDEX
    Explanations

    Bradford Northern

    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
    اÙĨÙĬ
    -0.10
    lob
    -0.10
    è¿Ķè¿ĺ
    -0.10
    ndo
    -0.09
    Knife
    -0.09
    avel
    -0.09
    folio
    -0.09
    Charlotte
    -0.08
    æīĢæıIJä¾Ľä¹ĭ
    -0.08
    ystone
    -0.08
    POSITIVE LOGITS
    pane
    0.09
    amer
    0.08
    èIJ½åIJİ
    0.08
    sm
    0.08
    sd
    0.08
    reme
    0.08
    è±Ĩ
    0.08
    dm
    0.08
    alog
    0.08
    ç²²
    0.08
    Activations Density 0.005%

    No Known Activations