© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1635
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
     Literary
    -0.22
    E
    -0.21
    ÑĤÑĮ
    -0.21
    æľĹ诵
    -0.20
    (FALSE
    -0.20
    _unix
    -0.20
    ä»ĭ
    -0.20
    (False
    -0.20
     clouds
    -0.20
     hover
    -0.20
    POSITIVE LOGITS
    oons
    0.25
    æģĻ
    0.23
    ä»»
    0.22
    åı¯ä»¥ä½¿
    0.22
    cai
    0.22
    rende
    0.21
    å·¥æľŁ
    0.21
    áĢŁ
    0.21
    -other
    0.21
    dog
    0.21
    Activations Density 0.024%

    No Known Activations