© 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. 2148
    Prev
    Next
    INDEX
    Explanations

    Mil usage random keywords conc operations Col

    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
    utors
    -0.24
    (curr
    -0.24
    oller
    -0.23
    ectl
    -0.23
    (rt
    -0.23
    ä¼ŀ
    -0.21
    utow
    -0.21
    ISON
    -0.21
     massages
    -0.21
    IMIT
    -0.21
    POSITIVE LOGITS
     Golden
    0.25
     Event
    0.24
    &#
    0.23
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.23
     AW
    0.22
     Word
    0.22
     G
    0.22
    èģĶç³»æĪij们
    0.21
     fug
    0.21
     anzeigen
    0.20
    Activations Density 0.024%

    No Known Activations