© 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. 1701
    Prev
    Next
    INDEX
    Explanations

    element property assignment

    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
    .AutoScaleMode
    -0.27
    èĥĮåIJİçļĦ
    -0.24
    .bunifuFlatButton
    -0.23
    alous
    -0.23
    åIJIJ
    -0.23
    rement
    -0.23
    ä¸Ĭä¸ĭ
    -0.23
    .palette
    -0.22
    ç¾²
    -0.22
    -sex
    -0.22
    POSITIVE LOGITS
     =
    0.26
     runaway
    0.25
    ä¸Ģ个æĸ°çļĦ
    0.23
    ight
    0.23
    0.23
    ³³³³³³³
    0.22
    ã«
    0.22
    æŵ
    0.22
    临æŶ
    0.21
    èĢĴ
    0.21
    Activations Density 0.575%

    No Known Activations