© 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. 2510
    Prev
    Next
    INDEX
    Explanations

    file extensions, abbreviations, or prefixes

    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
    xBD
    -0.28
    immers
    -0.24
    ,cp
    -0.22
    xbd
    -0.22
    xBB
    -0.22
    LOPT
    -0.22
    prompt
    -0.22
    xFC
    -0.21
    åĪº
    -0.21
    lod
    -0.21
    POSITIVE LOGITS
    è¿Ļä¸ī个
    0.26
    è¿Ļ个æĹ¶ä»£
    0.23
    è·ijåİ»
    0.23
     Recorder
    0.22
    æĬĬè¿Ļ个
    0.22
    åĪ°çİ°åľ¨
    0.22
    ë¥ł
    0.22
    гад
    0.22
    вез
    0.21
     Strict
    0.21
    Activations Density 0.006%

    No Known Activations