© 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. 22358
    Prev
    Next
    INDEX
    Explanations

    TV channel programming

    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
    æľ¬åľ°
    -0.09
    æĦıå¤ĸ
    -0.08
    è¿Ļä½į
    -0.08
    ÑĪÑĥ
    -0.08
     Rav
    -0.08
    两ä½į
    -0.08
    åĩłä½į
    -0.08
    LOCAL
    -0.08
    äºĮæīĭ
    -0.08
    ç¿»
    -0.08
    POSITIVE LOGITS
    çĬ¯ç½ª
    0.10
    rete
    0.09
    迷失
    0.09
    å¿ĥè¡Ģ
    0.09
     оÑĩеÑĢ
    0.09
    abyrin
    0.09
    翼
    0.09
    listed
    0.08
    æļĹ
    0.08
    Ñħи
    0.08
    Activations Density 0.009%

    No Known Activations