© 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. 49206
    Prev
    Next
    INDEX
    Explanations

    frontier and its related concepts

    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
    ollen
    -0.11
    lico
    -0.09
    Ïį
    -0.09
    æĶ¯æĮģåĬĽåº¦
    -0.09
    аÑĤелÑĮ
    -0.09
    uper
    -0.08
    æ²Ļ滩
    -0.08
    åŁİéĻħ
    -0.08
    ening
    -0.08
    åĩıåĢ¼
    -0.08
    POSITIVE LOGITS
    à¹Į
    0.11
    æĢ§å¼º
    0.11
    zek
    0.11
    /front
    0.10
    æĢ§çļĦ
    0.10
    liner
    0.10
    combe
    0.10
    composite
    0.09
    zeit
    0.09
    åīį沿
    0.09
    Activations Density 0.006%

    No Known Activations