© 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. 6460
    Prev
    Next
    INDEX
    Explanations

    road safety week and research

    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
    æĴ©
    -0.11
    åĤ»
    -0.09
    æĭ¿
    -0.09
    媳å¦ĩ
    -0.08
    tar
    -0.08
     ca
    -0.08
    ero
    -0.08
    æĬļ
    -0.08
    bd
    -0.08
    èĭį
    -0.08
    POSITIVE LOGITS
    ahoo
    0.09
     setters
    0.09
    å¤§éĽ¨
    0.09
    æ¸Ľå°ij
    0.09
    åĩıå°ij
    0.09
    ç¿°
    0.09
    大å®ĹåķĨåĵģ
    0.08
    vell
    0.08
    çŀĴ
    0.08
    .setter
    0.08
    Activations Density 0.021%

    No Known Activations