© 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. 5166
    Prev
    Next
    INDEX
    Explanations

    every/are/is

    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¸Ģç³»åĪĹ
    -0.11
    ä¸ĢåĪĩéĥ½
    -0.10
    è¶Ĭå¤ļ
    -0.10
    ä»»ä½ķæŶåĢĻ
    -0.10
    ä»»ä½ķ
    -0.09
    并ä¸į
    -0.09
    并ä¸įå¤ļ
    -0.09
    æ¯ıä¸Ģä½į
    -0.09
    ä¸įåģļ
    -0.09
    æŁIJäºĽ
    -0.09
    POSITIVE LOGITS
    è¿Ļä¹Ī大
    0.09
    ril
    0.08
    åĢ¼å¾Ĺä¸Ģ
    0.08
    éĿ¢ä¸´çĿĢ
    0.08
    cia
    0.08
    ison
    0.08
    åºĻ
    0.08
    éĥ½æľī
    0.08
    æ½ľåľ¨
    0.08
    èĢĮä¸Ķ
    0.08
    Activations Density 0.099%

    No Known Activations