© 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. 2207
    Prev
    Next
    INDEX
    Explanations

    Hollywood film and entertainment

    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
    ayah
    -0.21
    ä¸įä¿¡
    -0.20
    hta
    -0.19
    空æ°ĶåĩĢåĮĸ
    -0.19
    WINDOWS
    -0.19
    geber
    -0.19
    inel
    -0.18
    箩
    -0.18
    äºĨ大éĩıçļĦ
    -0.18
    lessly
    -0.18
    POSITIVE LOGITS
    shire
    0.30
    æ¹¾
    0.23
    icity
    0.23
    tail
    0.22
    sworth
    0.20
    à¸ĩ
    0.20
    gL
    0.20
     risk
    0.20
    ian
    0.20
    town
    0.19
    Activations Density 0.007%

    No Known Activations