© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    waterfront and front locations

    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
    离
    -0.26
    pell
    -0.24
    æ°¨éħ¸
    -0.21
    -strong
    -0.21
    Sibling
    -0.21
    åľº
    -0.21
    åĽ½ç±į
    -0.21
    ä¹İ
    -0.21
    éĽ¢
    -0.21
    flows
    -0.21
    POSITIVE LOGITS
    icher
    0.25
    anship
    0.24
    INDER
    0.23
    ancy
    0.23
    idential
    0.22
     assets
    0.22
    ict
    0.22
     nowrap
    0.22
    acter
    0.21
    ä¸ĬçļĦ
    0.21
    Activations Density 0.004%

    No Known Activations