© 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. 17738
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    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
    伪
    -0.09
    ith
    -0.09
    å¾Ī好
    -0.08
    æĢĢ
    -0.08
    ãĥīãĥ©
    -0.08
    æĢ§å¼º
    -0.08
    _suite
    -0.08
    iron
    -0.08
    ail
    -0.08
    京
    -0.08
    POSITIVE LOGITS
    å¤§åľ°
    0.10
    usercontent
    0.10
    ä½łä¼ļåıijçİ°
    0.10
    åĪĨå±Ģ
    0.09
    æĿĤå¿Ĺ社
    0.09
    æ·ij
    0.09
    inas
    0.08
    缧
    0.08
    ths
    0.08
    annes
    0.08
    Activations Density 0.266%

    No Known Activations