© 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. 9881
    Prev
    Next
    INDEX
    Explanations

    email addresses or @ symbols

    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
    å®ĺç½ij
    -0.11
    ìĬµ
    -0.10
    mate
    -0.09
    uter
    -0.09
    å§Ĭ妹
    -0.09
    çļĦçIJĨ解
    -0.09
     Exceptions
    -0.08
    ×Ļ×ŀ×ķ
    -0.08
    妳
    -0.08
    APT
    -0.08
    POSITIVE LOGITS
    ä¸Ģå°ģ
    0.09
    lest
    0.09
    æİī
    0.08
    @
    0.08
     firstname
    0.08
    [email
    0.08
    èħ³
    0.08
    åijĬ
    0.08
    _within
    0.08
    .firstname
    0.08
    Activations Density 0.145%

    No Known Activations