© 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. 34545
    Prev
    Next
    INDEX
    Explanations

    OpenSSL, card, Project

    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
    ichte
    -0.09
    ä¸Ģ线
    -0.09
    ToFront
    -0.09
    驱
    -0.09
    rant
    -0.08
    ilater
    -0.08
     Relief
    -0.08
    奢
    -0.08
     relief
    -0.08
    éĥħ
    -0.08
    POSITIVE LOGITS
     Petit
    0.10
     ÑħÑĢ
    0.09
    è½½ä½ĵ
    0.09
    座
    0.08
    avl
    0.08
    anas
    0.08
    PELL
    0.08
    éģŀ
    0.08
    _rng
    0.08
    橹
    0.08
    Activations Density 0.180%

    No Known Activations