© 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. 2611
    Prev
    Next
    INDEX
    Explanations

    at times

    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
    éĢļ常æĺ¯
    -0.29
    éĢļ常
    -0.28
    åIJİåĨį
    -0.25
    индивид
    -0.25
     usually
    -0.25
     rekl
    -0.24
     typically
    -0.24
     Usually
    -0.23
     entsprech
    -0.22
     usu
    -0.22
    POSITIVE LOGITS
     downright
    0.26
    Even
    0.26
     sogar
    0.24
     resembled
    0.24
    even
    0.23
    -fi
    0.23
    åIJĥ
    0.23
    ç®Ģ缴æĺ¯
    0.23
    çĶļèĩ³æĺ¯
    0.23
     resembl
    0.23
    Activations Density 0.019%

    No Known Activations