© 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. 49091
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    주ìĿĺ
    -0.10
    åı¸
    -0.10
    usalem
    -0.10
    оваÑĤÑĮ
    -0.09
    è¾ĸ
    -0.09
    _PS
    -0.09
    åħ¨è¦ĨçĽĸ
    -0.08
    swire
    -0.08
     Redistributions
    -0.08
    colo
    -0.08
    POSITIVE LOGITS
    4
    0.08
    9
    0.08
     ва
    0.08
    ENTE
    0.08
    æ¸ļ
    0.08
    3
    0.08
    2
    0.08
    -fly
    0.08
    fieldname
    0.08
    æĭĴ
    0.08
    Activations Density 0.000%

    No Known Activations