© 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. 7279
    Prev
    Next
    INDEX
    Explanations

    occasional, repeatedly, twice

    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
    æĹłå½¢
    -0.11
    æĹ©æĹ©
    -0.10
    ä¸Ģè·¯ä¸Ĭ
    -0.10
    æĺ¼å¤ľ
    -0.10
    els
    -0.10
    _DEVICES
    -0.10
    æĹ©çĤ¹
    -0.10
    phia
    -0.09
    æľ¬åľŁ
    -0.09
    æĻĶ
    -0.09
    POSITIVE LOGITS
    åģ¶å°Ķ
    0.16
    åģ¶
    0.14
    临æŶ
    0.13
    åĩłæ¬¡
    0.13
     occasional
    0.12
    ä¸Ģ次
    0.11
    éĤ£æ¬¡
    0.11
    å°ijéĩı
    0.10
    ä¸į代表
    0.10
    åģ¶çĦ¶
    0.10
    Activations Density 0.096%

    No Known Activations