© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 123
    Prev
    Next
    INDEX
    Explanations

    optional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ç»ĻåĬĽ
    -0.25
    ä¸Ģå®ļç¨ĭ度
    -0.25
    å¾Ī大ç¨ĭ度
    -0.24
    ÃŃd
    -0.23
     überhaupt
    -0.23
    yne
    -0.23
    füg
    -0.23
    arat
    -0.23
    igest
    -0.23
    Ĩµ
    -0.23
    POSITIVE LOGITS
     further
    0.30
     briefly
    0.30
     OPTIONAL
    0.28
    Optional
    0.28
    (optional
    0.27
    为æĤ¨
    0.27
    optional
    0.26
     vain
    0.26
     Optional
    0.26
    并对
    0.26
    Activations Density 0.015%

    No Known Activations