© 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. 31645
    Prev
    Next
    INDEX
    Explanations

    spots or places available

    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
    é«ĺæ½®
    -0.11
    æıĦ
    -0.11
    éķ«
    -0.09
    reck
    -0.09
     Iso
    -0.09
    HELL
    -0.09
    èĥĮéĿ¢
    -0.09
    _visitor
    -0.09
    rike
    -0.08
    è¢ľ
    -0.08
    POSITIVE LOGITS
    å¸Ń
    0.12
    åIJįé¢Ŀ
    0.11
     spots
    0.11
     seats
    0.10
    .slot
    0.10
     spot
    0.10
     positions
    0.09
    slot
    0.09
    åºĶ该æĢİä¹Ī
    0.09
    ç«ĭ足
    0.09
    Activations Density 0.073%

    No Known Activations