© 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. 54780
    Prev
    Next
    INDEX
    Explanations

    torque

    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
    º
    -0.10
    liness
    -0.10
    bum
    -0.09
    .CV
    -0.09
    ак
    -0.08
    rss
    -0.08
     COPYING
    -0.08
    оÑī
    -0.08
    reck
    -0.08
    iment
    -0.08
    POSITIVE LOGITS
    éĢįéģ¥
    0.10
    tat
    0.10
    tors
    0.09
    èĩªçĦ¶èĢĮ
    0.09
    天çĶŁ
    0.09
    eur
    0.09
    èĽŁ
    0.09
    èIJ±
    0.09
    alis
    0.09
    ä¸įåľ¨ä¹İ
    0.09
    Activations Density 0.017%

    No Known Activations