© 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. 16950
    Prev
    Next
    INDEX
    Explanations

    inf or infer

    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
    edException
    -0.14
    itre
    -0.10
    ../../../
    -0.10
    æĦıæĥ³ä¸įåĪ°
    -0.09
    IAM
    -0.09
    IZE
    -0.09
    æĮŁ
    -0.09
    wise
    -0.09
    аÑĢа
    -0.09
    Ùģس
    -0.09
    POSITIVE LOGITS
    rence
    0.12
    侧ç»ĵæŀĦæĢ§
    0.10
    ividual
    0.10
    æĸ¯å¡Ķ
    0.10
    åĭĥåĭĥ
    0.09
    estr
    0.09
    åīįæīĢ
    0.09
    hoot
    0.09
    resco
    0.09
    ضÙĦ
    0.09
    Activations Density 0.052%

    No Known Activations