© 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. 36513
    Prev
    Next
    INDEX
    Explanations

    fragmented, dispersed, separate, split

    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
    éĩijå±±
    -0.11
    æĮģå¹³
    -0.10
    çķľ
    -0.10
    imson
    -0.09
    æĹłå£°
    -0.09
     Dominion
    -0.09
    ä¼ļ计å¸Ī
    -0.09
    åĻĮ
    -0.08
    çīºçī²
    -0.08
    èĤī
    -0.08
    POSITIVE LOGITS
    åĪĨæķ£
    0.21
    ç¢İçīĩ
    0.16
     scattered
    0.15
     pie
    0.15
    æķ£
    0.14
    鼶ç¢İ
    0.13
     Fragment
    0.13
    æķ£å¸ĥ
    0.13
    ç¢İ
    0.12
     fragmented
    0.12
    Activations Density 0.101%

    No Known Activations