© 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. 63093
    Prev
    Next
    INDEX
    Explanations

    par followed by specific suffixes

    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
    ellt
    -0.09
    맵
    -0.09
    exter
    -0.09
    å£ij
    -0.09
    affer
    -0.09
    ement
    -0.09
    unes
    -0.09
    ustin
    -0.09
    empo
    -0.09
    eger
    -0.09
    POSITIVE LOGITS
    çİ°åĩº
    0.10
     Ñģобой
    0.09
    åij¨åĽ´çļĦ
    0.09
    tridge
    0.08
    mint
    0.08
    quet
    0.08
    most
    0.08
    ry
    0.08
    é¾Ļæ³ī
    0.08
    éĢĤå®ľ
    0.08
    Activations Density 0.016%

    No Known Activations