© 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. 1942
    Prev
    Next
    INDEX
    Explanations

    september 11

    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
    uche
    -0.24
    çİĭåħĪçĶŁ
    -0.23
     prés
    -0.22
    ä¼łçľŁ
    -0.22
    евиÑĩ
    -0.21
     TORT
    -0.21
    åħīæĺİ
    -0.21
    åŀĭä¼ģä¸ļ
    -0.21
    ucha
    -0.20
     getX
    -0.20
    POSITIVE LOGITS
    å½¢æĪIJäºĨ
    0.27
    expert
    0.22
     scenario
    0.21
     completo
    0.21
    éĵ¾æĿ¡
    0.21
    å½¢æĪIJ
    0.20
    ä¸IJ
    0.20
    éĢłæĪIJäºĨ
    0.20
    sm
    0.20
     slam
    0.20
    Activations Density 0.001%

    No Known Activations