© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    http links and licenses

    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
     combo
    -0.27
    <|endoftext|>
    -0.23
     area
    -0.23
    TV
    -0.23
     drum
    -0.23
     crazy
    -0.22
     TV
    -0.22
     food
    -0.22
     conversation
    -0.22
     sno
    -0.22
    POSITIVE LOGITS
     Bibli
    0.26
    èĢĮéĿŀ
    0.26
    导读
    0.26
    åı²æĸĻ
    0.26
    读èĢħ
    0.26
     ePub
    0.26
    åİŁèijĹ
    0.26
    çŁ¥è¯ĨåĪĨåŃIJ
    0.25
     materially
    0.25
     Copies
    0.25
    Activations Density 0.518%

    No Known Activations