© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7983
    Prev
    Next
    INDEX
    Explanations

    school grade levels

    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
    è®®äºĭ
    -0.10
    è¿ľç¦»
    -0.09
    éĢ
    -0.09
    otec
    -0.09
    议论
    -0.09
    usch
    -0.09
    HING
    -0.08
    çŃĿ
    -0.08
    Intialized
    -0.08
    ITCH
    -0.08
    POSITIVE LOGITS
    驽
    0.09
    å¢ĥ
    0.09
    aits
    0.08
    -aged
    0.08
    Pts
    0.08
    çķĮçļĦ
    0.08
    -ready
    0.08
    _pull
    0.08
    orno
    0.08
     gor
    0.08
    Activations Density 0.008%

    No Known Activations