© 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. 55802
    Prev
    Next
    INDEX
    Explanations

    ideals and beliefs

    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
    æĸ°å¸¸æĢģ
    -0.09
     Autor
    -0.09
    常æĢģ
    -0.09
    agli
    -0.09
    apot
    -0.08
    æīĵçł´
    -0.08
    IFIC
    -0.08
    енÑĮк
    -0.08
    odb
    -0.08
    æīĵçł´äºĨ
    -0.07
    POSITIVE LOGITS
    信念
    0.15
     ideals
    0.13
    çIJĨ念
    0.12
    çļĦçIJĨ念
    0.12
    ä¿¡ä»°
    0.12
    çIJĨæĥ³çļĦ
    0.11
    åĿļå®Ī
    0.11
    æĦ¿æĻ¯
    0.11
    认åı¯
    0.11
     passionate
    0.11
    Activations Density 0.069%

    No Known Activations