© 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. 48377
    Prev
    Next
    INDEX
    Explanations

    peace and related concepts

    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
    ascus
    -0.11
    ãģĦãĤĭ
    -0.11
    mente
    -0.10
    æ·±åĮĸæĶ¹éĿ©
    -0.10
    amarin
    -0.09
    te
    -0.09
    tes
    -0.09
    æĭ©
    -0.09
    ts
    -0.09
    lah
    -0.09
    POSITIVE LOGITS
    vro
    0.09
    kick
    0.09
    .gov
    0.09
    keeping
    0.09
    vous
    0.09
    cly
    0.09
    ellen
    0.09
    able
    0.09
    hurst
    0.09
    çĴIJ
    0.08
    Activations Density 0.005%

    No Known Activations