© 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. 472
    Prev
    Next
    INDEX
    Explanations

    fashion, food, tastiness

    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
    CharacterSet
    -0.28
    ernes
    -0.27
    fdc
    -0.26
    /legal
    -0.26
    iping
    -0.25
    ushima
    -0.25
    Regs
    -0.25
    arna
    -0.24
    UserCode
    -0.24
    ailer
    -0.24
    POSITIVE LOGITS
     Fashion
    0.32
     fatt
    0.29
     aesthetic
    0.28
     Gallery
    0.28
     Magazine
    0.28
     tasty
    0.27
     food
    0.27
     flips
    0.27
     flipping
    0.26
     Food
    0.26
    Activations Density 0.021%

    No Known Activations