© 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. 2435
    Prev
    Next
    INDEX
    Explanations

    couldn't find/get/make

    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
    æľīéĹ®é¢ĺ
    -0.27
    abouts
    -0.24
    OrUpdate
    -0.24
    çİ©æĦı
    -0.23
    çīĪæĿĥ声æĺİ
    -0.23
    ä¸įç»ı
    -0.23
    ä¸įéĶĻçļĦ
    -0.22
    pretty
    -0.21
    heet
    -0.21
    affer
    -0.20
    POSITIVE LOGITS
     ascertain
    0.23
     reconcile
    0.23
    æĶ»åĿļ
    0.21
    pt
    0.20
     reconc
    0.20
     ITE
    0.19
    uja
    0.18
    ****************************************************************************
    0.18
    ت
    0.18
    ed
    0.18
    Activations Density 0.037%

    No Known Activations