© 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. 917
    Prev
    Next
    INDEX
    Explanations

    unique things and phenomena

    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
    èŀºæĹĭ
    -0.23
     renegot
    -0.23
     Linkedin
    -0.22
     supervisors
    -0.21
     дополниÑĤелÑĮно
    -0.21
    èĢģ人家
    -0.21
    ä½İä½į
    -0.21
     Affero
    -0.21
    éķ¥
    -0.21
    _approval
    -0.20
    POSITIVE LOGITS
    (""
    0.22
    ings
    0.21
     yazılı
    0.21
    ply
    0.21
    nst
    0.21
    éĤķ
    0.20
     tuo
    0.20
    su
    0.20
    ç§ijå°Ķ
    0.20
     ngôi
    0.20
    Activations Density 0.711%

    No Known Activations