© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20910
    Prev
    Next
    INDEX
    Explanations

    presidential names

    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
    åŃIJéĩĮ
    -0.12
    ugg
    -0.10
    ally
    -0.10
    ached
    -0.10
    好转
    -0.09
    ³
    -0.09
    ocha
    -0.09
    fully
    -0.09
    ilyn
    -0.08
    ðŁı»
    -0.08
    POSITIVE LOGITS
    ãģıãĤĮ
    0.11
    ино
    0.10
    rels
    0.09
    hausen
    0.09
    ino
    0.09
    ieri
    0.09
    sWith
    0.09
    à¹Į
    0.09
    redient
    0.08
    лиÑĤ
    0.08
    Activations Density 0.016%

    No Known Activations