© 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. 52466
    Prev
    Next
    INDEX
    Explanations

    you may choose

    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
    æķĻèĤ²èµĦæºIJ
    -0.10
    kok
    -0.09
    åıĪ好
    -0.09
    ä¸ĢèĦļ
    -0.09
     mặc
    -0.09
    è²Įä¼¼
    -0.09
    èij©
    -0.09
    çŃīå¥ĸ
    -0.09
    MAND
    -0.08
    åı¦å¤ĸä¸Ģ个
    -0.08
    POSITIVE LOGITS
    omon
    0.09
    åij½ä¸Ń
    0.08
    éĢĤ
    0.08
    gon
    0.08
    _aug
    0.08
     reim
    0.08
     ONLINE
    0.08
    åĨįéĢł
    0.08
    nett
    0.08
    _membership
    0.07
    Activations Density 0.082%

    No Known Activations