© 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. 57295
    Prev
    Next
    INDEX
    Explanations

    hatch, hatching, Pope Francis

    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
    plete
    -0.10
    تÙĪÙĨ
    -0.09
    think
    -0.09
    ĺ
    -0.09
    íģ¼
    -0.08
    <![
    -0.08
    çĦ¦çĤ¹
    -0.08
    æĮĿ
    -0.08
    æĸ¯é¡¿
    -0.08
    uelle
    -0.08
    POSITIVE LOGITS
    ling
    0.11
    lings
    0.11
    atched
    0.10
    ʲ
    0.10
    pole
    0.09
    اÙĥ
    0.09
    åŃIJéĩĮ
    0.09
    Ùħب
    0.09
    æĪij们å¿ħé¡»
    0.09
    lene
    0.09
    Activations Density 0.009%

    No Known Activations