© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 30219
    Prev
    Next
    INDEX
    Explanations

    hear about

    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
    eur
    -0.11
    ari
    -0.09
    atem
    -0.08
    olv
    -0.08
    Harness
    -0.08
    ion
    -0.08
     pict
    -0.08
    ç»Ļåĩº
    -0.08
    /in
    -0.08
    æ§Ĭ
    -0.08
    POSITIVE LOGITS
    kest
    0.10
    гÑĥ
    0.10
    stry
    0.10
    kening
    0.10
    abouts
    0.09
    oused
    0.09
    /read
    0.09
    ä¸ĢåIJ¬
    0.09
    ä¸Ģéģį
    0.09
    WARE
    0.09
    Activations Density 0.017%

    No Known Activations