© 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. 32741
    Prev
    Next
    INDEX
    Explanations

    physiological terms and relationships

    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
    hip
    -0.11
    ç½ij讯
    -0.10
    hips
    -0.10
    çĿĩ
    -0.10
    ç
    -0.10
    .createObject
    -0.10
    åľ¨æĪijçľĭæĿ¥
    -0.10
    ifest
    -0.09
    itel
    -0.09
    ifiable
    -0.09
    POSITIVE LOGITS
    åŃ¦å®¶
    0.10
    icians
    0.10
    ically
    0.09
    ively
    0.09
    enticator
    0.08
    anky
    0.08
    clin
    0.08
    ÙĩÙĪ
    0.08
    ters
    0.08
    goo
    0.08
    Activations Density 0.201%

    No Known Activations