© 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. 62936
    Prev
    Next
    INDEX
    Explanations

    Stephen followed by middle initial or name

    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
    вин
    -0.10
    aspers
    -0.09
    æĺŁçº§éħĴåºĹ
    -0.09
    تب
    -0.09
    uper
    -0.09
    çī¹åĪ«å£°æĺİ
    -0.09
    icare
    -0.09
    ties
    -0.09
    bone
    -0.09
    erah
    -0.09
    POSITIVE LOGITS
    aceous
    0.14
    XC
    0.09
    ery
    0.09
    sville
    0.09
    seite
    0.09
    isque
    0.09
    athan
    0.08
    trib
    0.08
    å¢Ł
    0.08
    angelo
    0.08
    Activations Density 0.035%

    No Known Activations