© 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. 36025
    Prev
    Next
    INDEX
    Explanations

    un- prefix, -ed suffix

    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
    èĢĮä¸įæĺ¯
    -0.12
    akens
    -0.10
    ä¸įèĥ½åĨį
    -0.10
    æīĵåĬ¨
    -0.09
    们éĥ½
    -0.09
    åı«å£°
    -0.09
    èĢĮéĿŀ
    -0.09
    _Rel
    -0.09
    itzer
    -0.08
    GenerationStrategy
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.14
    è¿ĩå¤ļ
    0.10
     yet
    0.10
    (Un
    0.10
     whatsoever
    0.10
    æĪĸå¤ļ
    0.10
    ä»»ä½ķ
    0.09
     Dy
    0.09
    ä¸Ŀ毫
    0.09
     سÙĪÙī
    0.09
    Activations Density 0.105%

    No Known Activations