© 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. 31783
    Prev
    Next
    INDEX
    Explanations

    Rick followed by 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
     gắng
    -0.11
    çĪ»
    -0.10
    бил
    -0.09
    arker
    -0.09
    inia
    -0.09
    лег
    -0.09
    wyn
    -0.09
    รà¸Ńà¸ĩ
    -0.09
    ร
    -0.09
    enticator
    -0.09
    POSITIVE LOGITS
    ision
    0.11
    anto
    0.11
    housing
    0.10
    ëŀĺ
    0.10
    ellaneous
    0.09
    side
    0.09
    fone
    0.09
    à¥IJ
    0.09
    ãģĵãĤĵ
    0.09
    iness
    0.09
    Activations Density 0.004%

    No Known Activations