© 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. 23938
    Prev
    Next
    INDEX
    Explanations

    custody or practice

    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
    åľ¨éĩĮéĿ¢
    -0.09
    usher
    -0.09
     Instruments
    -0.08
    ARIO
    -0.08
    äºĭåıij
    -0.08
    IFIC
    -0.08
    æĦł
    -0.08
    èĺ¸
    -0.08
    èŁĭ
    -0.08
    å¥ĩ
    -0.08
    POSITIVE LOGITS
    ä¸įè´Ł
    0.11
    伶
    0.09
    åħ±é¸£
    0.09
    渲
    0.09
    CHASE
    0.09
    anas
    0.09
    ä¸Ńãģ®
    0.09
    对çħ§æ£ĢæŁ¥
    0.09
    轨
    0.08
    æ®Ĭ
    0.08
    Activations Density 0.201%

    No Known Activations