© 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. 2531
    Prev
    Next
    INDEX
    Explanations

    tuning or tune-related words

    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
    累累
    -0.20
    ¥
    -0.20
     Turnbull
    -0.19
     Meal
    -0.19
     mj
    -0.19
    unde
    -0.18
    ../../../
    -0.18
    YPE
    -0.18
    KER
    -0.18
    èĵ¬åĭĥ
    -0.18
    POSITIVE LOGITS
    -down
    0.27
    gether
    0.26
    -ups
    0.25
    -up
    0.24
    phony
    0.23
    åĻ¨
    0.23
    AndGet
    0.22
    egral
    0.20
    azzi
    0.20
    /control
    0.19
    Activations Density 0.015%

    No Known Activations