© 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. 50278
    Prev
    Next
    INDEX
    Explanations

    wordpress file paths and structures

    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
    åĴĮåľ°åĮº
    -0.10
    lining
    -0.10
    sticks
    -0.09
    iez
    -0.09
    éĤ£æŶåĢĻ
    -0.09
    家ä¼Ļ
    -0.08
    大å¦Ī
    -0.08
    æł¹æį®èĩªå·±
    -0.08
    и
    -0.08
    liner
    -0.08
    POSITIVE LOGITS
    å±ij
    0.10
    arent
    0.09
    chein
    0.09
     seam
    0.08
    .random
    0.08
    aro
    0.08
    ìľ¤
    0.08
    ubes
    0.08
    digest
    0.08
    Č
    0.08
    Activations Density 0.078%

    No Known Activations