© 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. 39209
    Prev
    Next
    INDEX
    Explanations

    U.S. representatives' surnames

    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
    çľģæĶ¿åºľ
    -0.12
     offending
    -0.09
     Mü
    -0.09
     bottles
    -0.09
    rial
    -0.08
    _inc
    -0.08
     Texans
    -0.08
    çĵ¶
    -0.08
     bottle
    -0.08
    è±¹
    -0.08
    POSITIVE LOGITS
     opposite
    0.10
    座
    0.09
    rade
    0.09
    apur
    0.09
    鸿
    0.09
    odia
    0.08
    edException
    0.08
     Vote
    0.08
    RAFT
    0.08
    代表
    0.08
    Activations Density 0.044%

    No Known Activations