© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 585
    Prev
    Next
    INDEX
    Explanations

    definition or explanation

    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
     Fires
    -0.23
    BSD
    -0.22
    datatype
    -0.21
     Ribbon
    -0.21
    wu
    -0.21
     recruit
    -0.21
    亲
    -0.21
     Accepted
    -0.20
     Garden
    -0.20
    umu
    -0.20
    POSITIVE LOGITS
    ivo
    0.27
    rophe
    0.25
    agli
    0.24
    raph
    0.23
    æµģåħ¥
    0.23
    èĦ±
    0.21
     ENG
    0.21
    ÑģÑĤÑĢа
    0.21
    ä¸Ĭè¿°
    0.20
    çļĦå°±æĺ¯
    0.20
    Activations Density 0.242%

    No Known Activations