© 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. 18183
    Prev
    Next
    INDEX
    Explanations

    choice + noun

    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
    _GAP
    -0.10
    è´¢è¿IJ
    -0.09
    uers
    -0.08
    çī¹åĪ«å£°æĺİ
    -0.08
     Bravo
    -0.08
    åĶ®åIJİ
    -0.08
    utar
    -0.08
    ãĥ¼ãĥł
    -0.08
    alic
    -0.08
    mlin
    -0.08
    POSITIVE LOGITS
    ness
    0.10
    ly
    0.09
    osg
    0.09
     Vog
    0.09
    è¿Ļ对
    0.09
    åĮĹç¾İ
    0.08
    LY
    0.08
    飫
    0.08
    æĸ°æĶ¿
    0.08
    èĵį
    0.08
    Activations Density 0.014%

    No Known Activations