© 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. 1529
    Prev
    Next
    INDEX
    Explanations

    marketplace and commonplace places

    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
    ted
    -0.34
    mers
    -0.27
    ستاÙĨ
    -0.23
    tte
    -0.23
    sWith
    -0.23
    aries
    -0.23
    ìĤ¬íķŃ
    -0.22
    ded
    -0.22
     quadr
    -0.22
    lage
    -0.22
    POSITIVE LOGITS
    utter
    0.22
    ä¼ļåIJĮ
    0.22
    ç¼İ
    0.21
    of
    0.21
    utom
    0.20
    unders
    0.20
    urn
    0.20
     Agreement
    0.20
    åķ¶
    0.19
    ikes
    0.19
    Activations Density 0.004%

    No Known Activations