© 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. 4401
    Prev
    Next
    INDEX
    Explanations

    digit 2 followed by punctuation or words

    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
    ../
    -0.18
    ../../../
    -0.16
    ../../
    -0.14
    ãģĦãģı
    -0.11
    uez
    -0.10
    uck
    -0.10
    оÑģÑĮ
    -0.10
    ../../../../
    -0.10
    äºĽ
    -0.10
    ields
    -0.09
    POSITIVE LOGITS
    nd
    0.18
    -thirds
    0.17
    /th
    0.10
    nds
    0.10
    ä¸Ģ个æĺ¯
    0.09
    ãģ°
    0.09
    人å±ħ
    0.08
    orf
    0.08
    arily
    0.08
    ened
    0.08
    Activations Density 1.385%

    No Known Activations