© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51128
    Prev
    Next
    INDEX
    Explanations

    contemporary art, aesthetics, experiences, fears

    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
    ä¸įéĢļ
    -0.10
    lessly
    -0.09
    åĦ¿
    -0.09
    Unnamed
    -0.09
    enn
    -0.09
    esthetic
    -0.09
    cher
    -0.09
    -0.08
    ian
    -0.08
    累累
    -0.08
    POSITIVE LOGITS
    ä¹ĭä½ľ
    0.12
    erno
    0.11
    cy
    0.10
    æĢĨ
    0.10
    ä¹ĭåĬ¿
    0.10
    aneously
    0.09
    åıijè§ī
    0.09
    é£İè²Į
    0.09
    ä½ľé£İ
    0.09
    ä¹ĭéĻħ
    0.09
    Activations Density 0.007%

    No Known Activations