© 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. 21724
    Prev
    Next
    INDEX
    Explanations

    grain and grains

    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
    ../../../
    -0.15
    ðŁı»
    -0.11
    itarian
    -0.11
    çİ¢
    -0.10
    ãĤį
    -0.10
    ðŁı¼
    -0.10
    Aqu
    -0.10
    迤
    -0.10
    ibility
    -0.09
    oley
    -0.09
    POSITIVE LOGITS
    lessly
    0.12
    ãģªãĤĬ
    0.11
    onal
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    วย
    0.09
    iac
    0.09
    edList
    0.09
    ingly
    0.08
    æ»ļæ»ļ
    0.08
    ur
    0.08
    Activations Density 0.009%

    No Known Activations