© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38544
    Prev
    Next
    INDEX
    Explanations

    data processing and management

    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
    ned
    -0.10
    ï¸
    -0.10
    é¢Ŀ度
    -0.09
    bas
    -0.09
    çıı
    -0.09
     lẽ
    -0.09
    åŃIJéĩĮ
    -0.09
    æķ°æį®ä¸Ńå¿ĥ
    -0.09
    edList
    -0.09
    nen
    -0.09
    POSITIVE LOGITS
    ils
    0.16
    ë²ł
    0.13
    -testid
    0.12
    flow
    0.11
    ë§Ŀ
    0.11
    ìħĭ
    0.11
    frames
    0.11
    -aos
    0.11
    aru
    0.10
    .SqlClient
    0.10
    Activations Density 0.176%

    No Known Activations