© 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. 50628
    Prev
    Next
    INDEX
    Explanations

    not just

    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¸įå¿ħ
    -0.10
    ä¸įåĨįæĺ¯
    -0.10
    åĨįä¹Łæ²¡æľī
    -0.09
    ëĿ½
    -0.09
    æľĢå¤ļ
    -0.09
    ä¸įå°ij人
    -0.09
    ä½£
    -0.09
    ä¸Ģä¸ĩ
    -0.09
    /of
    -0.08
    견
    -0.08
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.11
    ifications
    0.10
    ifiable
    0.10
    åįķ纯çļĦ
    0.10
    ifying
    0.10
    èĢĮæĿ¥
    0.09
    ifies
    0.09
    ions
    0.09
    å±ĢéĻIJäºİ
    0.09
    çĽ²çĽ®
    0.09
    Activations Density 0.012%

    No Known Activations