© 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. 27063
    Prev
    Next
    INDEX
    Explanations

    Pepsi IPL, peptic ulcer

    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
    æijĦ
    -0.09
    orton
    -0.08
    âĪ
    -0.08
    uns
    -0.08
    å¨ģå°Ķ
    -0.08
    责令
    -0.08
    ä¾ĽéľĢ
    -0.08
    zelf
    -0.08
    çī²
    -0.08
    è¡
    -0.08
    POSITIVE LOGITS
    riad
    0.10
     tòa
    0.09
    rô
    0.09
    éĺļ
    0.09
    RITE
    0.08
    èķĥ
    0.08
    rias
    0.08
    ак
    0.08
    å¨ĺ家
    0.08
    rike
    0.08
    Activations Density 0.002%

    No Known Activations