© 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. 4911
    Prev
    Next
    INDEX
    Explanations

    for purpose

    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
    çıĤ
    -0.09
    ä¸ĢåĪĨ
    -0.09
    aos
    -0.09
    å·´
    -0.08
    usher
    -0.08
    丼æŀĹ
    -0.08
    unsch
    -0.08
    år
    -0.08
    ä¸Ģ大
    -0.08
     DISP
    -0.08
    POSITIVE LOGITS
    éĤ£äºĽ
    0.10
    è°ĥéħį
    0.09
    çļĦæĺ¯
    0.09
    大èĥĨ
    0.08
    orative
    0.08
    æĭĪ
    0.08
    çŁ£
    0.08
    voy
    0.08
    大å±Ģ
    0.08
    .mu
    0.08
    Activations Density 0.045%

    No Known Activations