© 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. 875
    Prev
    Next
    INDEX
    Explanations

    t-shirt and clothes

    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
    defer
    -0.26
    è¸ıä¸Ĭ
    -0.24
    éĨ´
    -0.23
    mites
    -0.22
    ichte
    -0.22
    äºŁ
    -0.21
    mts
    -0.21
    ldb
    -0.21
    åĮĸè¿Ľç¨ĭ
    -0.21
    ÃŃch
    -0.21
    POSITIVE LOGITS
    è¡«
    0.44
     shirt
    0.40
     shirts
    0.38
     jacket
    0.31
     clothes
    0.29
     hoodie
    0.28
     sweater
    0.28
    åĨħè¡£
    0.27
    shirt
    0.27
    ropa
    0.26
    Activations Density 0.020%

    No Known Activations