© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21529
    Prev
    Next
    INDEX
    Explanations

    match

    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
    ance
    -0.11
    istance
    -0.11
    aming
    -0.10
    ĺ
    -0.09
    isl
    -0.09
    ë¦Ħ
    -0.09
    este
    -0.09
    客æĪ·æıIJä¾Ľ
    -0.09
    ãĤģ
    -0.08
    eday
    -0.08
    POSITIVE LOGITS
    ãĥ³ãĤ°
    0.17
    ingly
    0.11
    alysis
    0.11
    ãĥ§
    0.11
    sticks
    0.10
    ä¸įä¸Ĭ
    0.10
    heet
    0.10
    DispatchToProps
    0.10
    tures
    0.10
    ings
    0.10
    Activations Density 0.037%

    No Known Activations