© 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. 38074
    Prev
    Next
    INDEX
    Explanations

    inns and innkeepers

    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
    naire
    -0.11
    anne
    -0.10
    ize
    -0.10
    eer
    -0.09
    éľĸ
    -0.09
    į
    -0.09
    å±ķæ¼Ķ
    -0.09
    ãģĦãģĨ
    -0.09
    ille
    -0.08
    parate
    -0.08
    POSITIVE LOGITS
    keepers
    0.14
    keeper
    0.13
    rement
    0.10
    ê¹IJ
    0.10
    -house
    0.09
    acionales
    0.09
    acional
    0.09
    人士
    0.09
    å°ıå·§
    0.09
    (crate
    0.09
    Activations Density 0.009%

    No Known Activations