© 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. 2396
    Prev
    Next
    INDEX
    Explanations

    Eric followed by a surname

    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
    spec
    -0.26
    orable
    -0.23
    iness
    -0.23
    ert
    -0.21
    edly
    -0.21
    arrays
    -0.21
    anan
    -0.21
    INGS
    -0.20
    ertext
    -0.20
    á»ĭch
    -0.20
    POSITIVE LOGITS
    amente
    0.29
    ally
    0.28
    aceous
    0.28
    ä¸ĢæĬĬ
    0.22
    ALLY
    0.22
    naire
    0.22
    arium
    0.21
    opath
    0.21
    noon
    0.20
    ção
    0.20
    Activations Density 0.015%

    No Known Activations