© 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. 2499
    Prev
    Next
    INDEX
    Explanations

    `_Cmd` or `.Command`

    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
    综åIJĪæĢ§
    -0.25
    .food
    -0.24
    Âł↵
    -0.24
     Âł Âł Âł Âł
    -0.22
     ↵↵
    -0.21
    userManager
    -0.20
    é¥®é£Ł
    -0.20
    aska
    -0.20
    Âł
    -0.20
    æ³Į
    -0.20
    POSITIVE LOGITS
    æĺ¯ä»ĸ
    0.23
    _Cmd
    0.22
    åĽłä¸ºå¥¹
    0.22
    (units
    0.22
    ä¸į失
    0.21
     Cage
    0.20
    æĽ·
    0.20
    .Command
    0.20
    allel
    0.20
     infer
    0.19
    Activations Density 0.332%

    No Known Activations