© 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. 6650
    Prev
    Next
    INDEX
    Explanations

    value of

    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
    çĦ¶æĺ¯
    -0.14
    ships
    -0.10
    aly
    -0.10
    ning
    -0.09
    el
    -0.09
    WithValue
    -0.09
    ERM
    -0.09
    ../../../
    -0.08
    med
    -0.08
    eced
    -0.08
    POSITIVE LOGITS
    0.15
    -added
    0.14
    -nil
    0.11
    (forKey
    0.11
    fully
    0.11
    鼷æĸ¯
    0.10
    æĬ¥éħ¬
    0.10
    -priced
    0.10
    hood
    0.10
    uetype
    0.10
    Activations Density 0.111%

    No Known Activations