© 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. 55964
    Prev
    Next
    INDEX
    Explanations

    still while and yet

    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
    nings
    -0.10
    æĽ´å¤ļ精彩
    -0.10
    è¿ľ
    -0.09
    éĿĴ
    -0.09
    VEN
    -0.09
    åĿ¦
    -0.09
    DOG
    -0.09
    ven
    -0.08
    å¹²èĦĨ
    -0.08
    æ¯Ķäºļ
    -0.08
    POSITIVE LOGITS
    ä»įçĦ¶
    0.16
     still
    0.15
    ä¸į失
    0.13
    ä»į
    0.13
    ä¾ĿçĦ¶
    0.13
    ä»įå°Ĩ
    0.12
    ä»įçĦ¶æĺ¯
    0.12
    åį´ä¸į
    0.11
    ä»įæŧ
    0.11
    still
    0.11
    Activations Density 0.221%

    No Known Activations