© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 1652
    Prev
    Next
    INDEX
    Explanations

    links, API, fifth, emitted, science, reversing, upper

    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
    #ab
    -0.27
    skin
    -0.24
    #ac
    -0.24
    说åΰè¿ĻéĩĮ
    -0.23
    _DD
    -0.22
    è§Ĵ
    -0.22
    볨
    -0.22
    eated
    -0.21
     Fault
    -0.21
    basket
    -0.21
    POSITIVE LOGITS
    ç¡®å®ŀ
    0.43
    ç¡®å®ŀæĺ¯
    0.41
    çļĦç¡®æĺ¯
    0.39
    çļĦç¡®
    0.38
     дейÑģÑĤвиÑĤелÑĮно
    0.34
    確實
    0.32
     indeed
    0.32
    ä½Ĩå®ĥ
    0.31
    ä¹Łåıªæĺ¯
    0.30
    åıªæĺ¯
    0.29
    Activations Density 0.315%

    No Known Activations