© 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. 55675
    Prev
    Next
    INDEX
    Explanations

    chocolate

    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
    acity
    -0.12
    äºĨ大éĩıçļĦ
    -0.11
    éĻħ
    -0.10
    ACITY
    -0.09
    åĭĥåĭĥ
    -0.09
    же
    -0.09
    åĴĮåľ°åĮº
    -0.09
    禽
    -0.09
    enga
    -0.09
    gom
    -0.08
    POSITIVE LOGITS
    eros
    0.10
    ercise
    0.10
    ype
    0.10
    .timing
    0.10
    ãģĦãģĨ
    0.09
    æł·çļĦ
    0.09
    berger
    0.09
    婵
    0.09
    åªĽ
    0.09
    à¸Ńาย
    0.09
    Activations Density 0.017%

    No Known Activations