© 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. 860
    Prev
    Next
    INDEX
    Explanations

    .h includes

    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
    est
    -0.38
    ed
    -0.34
    el
    -0.31
    es
    -0.30
    eval
    -0.30
    em
    -0.28
    ech
    -0.27
    ìľ¼ë¡ľ
    -0.26
    less
    -0.26
    element
    -0.26
    POSITIVE LOGITS
    inux
    0.36
    ibrary
    0.35
    mente
    0.34
    istic
    0.33
    anguage
    0.33
    ength
    0.32
    dehyde
    0.32
    ambda
    0.32
    ateral
    0.30
    ization
    0.30
    Activations Density 2.371%

    No Known Activations