© 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. 2423
    Prev
    Next
    INDEX
    Explanations

    numbers and variable assignments

    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
    éĢĴ交
    -0.23
    颦
    -0.22
    æĿĥçĽĬ
    -0.22
     деÑĢ
    -0.22
    alis
    -0.21
     Sass
    -0.21
    roid
    -0.21
    orie
    -0.21
    _hero
    -0.21
    abee
    -0.20
    POSITIVE LOGITS
    æ·®åįĹ
    0.25
    å¤ļäºĨ
    0.24
    路线
    0.23
    çļĦæĹ¥
    0.23
    asca
    0.23
    æŃ£åľ¨è¿Ľè¡Į
    0.22
    æįº
    0.22
     sırasında
    0.22
    IQUE
    0.22
    PLICIT
    0.22
    Activations Density 0.003%

    No Known Activations