© 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. 58277
    Prev
    Next
    INDEX
    Explanations

    Nickel, quarters, and cents

    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
    ubar
    -0.09
     пÑĢÑı
    -0.09
    åħīçݯ
    -0.08
    åŃ¦å®¶
    -0.08
     slate
    -0.08
    (fs
    -0.08
    lever
    -0.08
    ivity
    -0.08
     Lilly
    -0.08
    åįķä¸Ģ
    -0.08
    POSITIVE LOGITS
    hof
    0.09
    lit
    0.09
    enko
    0.09
    env
    0.09
    lon
    0.09
    _bootstrap
    0.09
    åľ¨ç½ij绾ä¸Ĭ
    0.09
    æ·¦
    0.09
    agon
    0.09
    çĮľ
    0.08
    Activations Density 0.005%

    No Known Activations