© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 625
    Prev
    Next
    INDEX
    Explanations

    hope it helps

    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
    DOI
    -0.24
    è¡Ķæİ¥
    -0.23
    åħħ满
    -0.23
     Operand
    -0.22
    èĤĨ
    -0.22
    å¨ĺ
    -0.21
    leitung
    -0.21
    áz
    -0.21
    è´¯
    -0.21
    atl
    -0.20
    POSITIVE LOGITS
    /close
    0.25
     lòng
    0.23
    çļĦæĥħåĨµä¸ĭ
    0.23
    icked
    0.23
    çļĦæľĭåıĭ
    0.22
    é²Ľ
    0.22
    /watch
    0.22
    _changed
    0.22
    并åIJij
    0.22
    rompt
    0.22
    Activations Density 0.008%

    No Known Activations