© 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. 2272
    Prev
    Next
    INDEX
    Explanations

    bean or beans

    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
    usions
    -0.23
    tar
    -0.20
     vast
    -0.19
    golden
    -0.18
    ta
    -0.18
    ours
    -0.18
    è´¿
    -0.18
    iple
    -0.18
    ght
    -0.18
     ë¶Ī구íķĺê³ł
    -0.18
    POSITIVE LOGITS
    ize
    0.20
    å¨ĺ
    0.19
    éļ
    0.19
    ////////////////////////////////////////////////////////
    0.19
    并ä¸İ
    0.18
    ized
    0.18
    楼
    0.18
    ////////////////////////////////////////////////////////////
    0.18
    -Mail
    0.18
    ////////////////////////////////////////////////
    0.18
    Activations Density 0.033%

    No Known Activations