© 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. 34474
    Prev
    Next
    INDEX
    Explanations

    scout and scouting related activities

    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
    ết
    -0.09
    nings
    -0.09
    ãĤĤãģ¡ãĤįãĤĵ
    -0.08
    throp
    -0.08
    å¾Ĺèµ·
    -0.08
    æķĻåѦ
    -0.08
    çĶŁäº§åĴĮ
    -0.08
    ãĤ³ãĥ¼ãĥ
    -0.08
    iances
    -0.08
    ningen
    -0.08
    POSITIVE LOGITS
    acular
    0.13
    eur
    0.10
    åŃIJå¼Ł
    0.10
    ÑĢид
    0.10
    fires
    0.10
    iegel
    0.09
    ural
    0.09
    åĵ¡
    0.09
    astic
    0.09
    å³Ń
    0.09
    Activations Density 0.004%

    No Known Activations