© 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. 2853
    Prev
    Next
    INDEX
    Explanations

    official organizations

    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
     Noon
    -0.25
    è±Ĩ
    -0.24
    æĬ±
    -0.23
    NOP
    -0.23
    rier
    -0.22
    irst
    -0.22
    ä¸Ģè´¯
    -0.22
    æĺ¯ä¸Ģ家
    -0.22
    è·Ŀ
    -0.22
     sting
    -0.22
    POSITIVE LOGITS
    -Pack
    0.25
    åĴĮæĬĢæľ¯
    0.22
     hazard
    0.22
    å±±åĮº
    0.21
    ToProps
    0.21
     smoothed
    0.20
     shelf
    0.20
     mor
    0.20
     interrupted
    0.20
     unsus
    0.20
    Activations Density 0.338%

    No Known Activations