© 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. 2986
    Prev
    Next
    INDEX
    Explanations

    sizes, width, bandwidth

    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
    HOOK
    -0.23
    Beh
    -0.23
    bone
    -0.22
    lik
    -0.22
    ìĪľ
    -0.22
    hone
    -0.21
    redient
    -0.21
    ough
    -0.21
    nde
    -0.21
    ivo
    -0.21
    POSITIVE LOGITS
     sizes
    0.56
    è§Ħæł¼
    0.52
     Sizes
    0.48
     size
    0.47
    sizes
    0.47
    OfSize
    0.47
    _sizes
    0.47
    尺寸
    0.46
     Size
    0.45
     sized
    0.45
    Activations Density 0.770%

    No Known Activations