© 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. 8043
    Prev
    Next
    INDEX
    Explanations

    voting and elections

    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
    å®Į好
    -0.11
    ä¸į幸
    -0.10
    lap
    -0.09
    碣
    -0.09
    TEX
    -0.09
    ft
    -0.08
    çľĭèijĹ
    -0.08
    (icon
    -0.08
    çĴĭ
    -0.08
    æıŃ
    -0.08
    POSITIVE LOGITS
    æĬķ票
    0.25
     voting
    0.22
     votes
    0.20
     vote
    0.20
     Voting
    0.20
    vote
    0.18
    _votes
    0.18
     Votes
    0.17
     voters
    0.17
     voter
    0.17
    Activations Density 0.096%

    No Known Activations