© 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. 32750
    Prev
    Next
    INDEX
    Explanations

    species, subspecies, or people v

    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
    èĭį
    -0.10
    åĩ½
    -0.09
    æŀĭ
    -0.09
    åħ¸åŀĭæ¡Īä¾ĭ
    -0.09
     Gren
    -0.08
    éħ·
    -0.08
    ä¸įèī¯
    -0.08
    ieux
    -0.08
     GOOGLE
    -0.08
    å¾Ī好
    -0.08
    POSITIVE LOGITS
    鸿
    0.11
    çªģ
    0.09
    ä¸Ģä¸ĩ
    0.09
    笺
    0.09
    è°¬
    0.09
    ä»·åĢ¼éĵ¾
    0.08
    é£ŀè·ĥ
    0.08
    éªĿ
    0.08
    欺éªĹ
    0.08
    éĤ£è¾¹
    0.08
    Activations Density 0.130%

    No Known Activations