© 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. 4868
    Prev
    Next
    INDEX
    Explanations

    better off

    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
    çľ¼è§Ĵ
    -0.10
    è¹Ī
    -0.09
     Amid
    -0.09
    级以ä¸Ĭ
    -0.09
    åı¤èĢģ
    -0.09
    æ´ģ
    -0.09
    ä¸Ńæĸ¹
    -0.09
    éĿłè°±
    -0.09
    icter
    -0.09
    eneg
    -0.09
    POSITIVE LOGITS
     simply
    0.10
    8
    0.10
    7
    0.10
    4
    0.10
    3
    0.09
    6
    0.09
    oin
    0.09
    2
    0.09
    9
    0.09
    5
    0.08
    Activations Density 0.017%

    No Known Activations