© 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. 1491
    Prev
    Next
    INDEX
    Explanations

    game of

    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
    è§Ĩ
    -0.26
    è¿ĻæĶ¯
    -0.24
    å¼ĤæĢ§
    -0.22
    /views
    -0.22
    /opt
    -0.22
    lez
    -0.21
    设æĸ½
    -0.21
    æľĢ好æĺ¯
    -0.21
    çĻ½å¤©
    -0.21
    åı£æĦŁ
    -0.21
    POSITIVE LOGITS
    estate
    0.28
    ront
    0.26
     estate
    0.25
    odial
    0.23
     fans
    0.23
     knights
    0.23
    phan
    0.22
    æľĪä¸Ń
    0.22
     Kane
    0.22
    lying
    0.22
    Activations Density 0.002%

    No Known Activations