© 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. 1078
    Prev
    Next
    INDEX
    Explanations

    Walker, Scott, Madam C.J., L.C. Arena

    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
    sWith
    -0.33
    ees
    -0.28
    egrate
    -0.26
    ervals
    -0.24
    ertext
    -0.24
    ailed
    -0.23
    ez
    -0.23
    enance
    -0.23
    ection
    -0.23
    eur
    -0.22
    POSITIVE LOGITS
    管å§Ķä¼ļ
    0.20
    fruit
    0.19
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.18
    ä¸įç»ıæĦı
    0.18
    st
    0.18
    æ¼¼
    0.18
     pursuits
    0.18
    عÙĨÙĬ
    0.18
    çĴ¥
    0.18
    ized
    0.18
    Activations Density 0.008%

    No Known Activations