© 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. 56048
    Prev
    Next
    INDEX
    Explanations

    endo

    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
     punch
    -0.09
    åĬ²
    -0.08
     streak
    -0.08
    ä½łæĢİä¹Ī
    -0.08
    eners
    -0.08
    rais
    -0.08
    itis
    -0.07
    èĬ±æł·
    -0.07
    次ä¼ļè®®
    -0.07
     punches
    -0.07
    POSITIVE LOGITS
    åĴİ
    0.10
    æĽ´å¤ļä¿¡æģ¯
    0.10
    é©·
    0.10
    ç¼Ķ
    0.10
    ardo
    0.09
    Insn
    0.09
    ãģıãĤĮ
    0.09
    Tower
    0.09
    åij¨ä¸ī
    0.09
    亲åĪĩ
    0.09
    Activations Density 0.001%

    No Known Activations