© 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. 54163
    Prev
    Next
    INDEX
    Explanations

    tutorial or tutorials

    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
    est
    -0.13
    主æĦı
    -0.10
     entirety
    -0.10
    -ever
    -0.09
    lessly
    -0.09
    å®°
    -0.09
    nable
    -0.09
    azen
    -0.09
    佬
    -0.08
    满äºĨ
    -0.08
    POSITIVE LOGITS
    ../../../
    0.12
    窿
    0.10
    åijĺ
    0.10
    ship
    0.10
    ously
    0.10
    ../../
    0.10
    е
    0.09
    ÑĢин
    0.09
    orris
    0.09
    ÑĢеÑģ
    0.09
    Activations Density 0.010%

    No Known Activations