© 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. 58234
    Prev
    Next
    INDEX
    Explanations

    message

    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
    shire
    -0.14
    side
    -0.11
    å¾Ĺä½ı
    -0.10
    lop
    -0.10
    ish
    -0.10
    erview
    -0.10
    Messenger
    -0.10
    thest
    -0.09
    quist
    -0.09
    ship
    -0.09
    POSITIVE LOGITS
    ioned
    0.11
    ãĥ³ãĤ°
    0.11
    /rfc
    0.11
    naire
    0.11
    hips
    0.10
    boards
    0.09
    éĩİ
    0.09
     curt
    0.08
    неж
    0.08
    antt
    0.08
    Activations Density 0.060%

    No Known Activations