© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 747
    Prev
    Next
    INDEX
    Explanations

    last item or person

    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
    åĴĶ
    -0.24
    chest
    -0.24
    ogo
    -0.24
     punching
    -0.23
    sha
    -0.23
    _fid
    -0.22
    ä¸İä¸ŃåĽ½
    -0.22
    Ļ¨
    -0.22
    .ru
    -0.22
    arians
    -0.21
    POSITIVE LOGITS
     finally
    0.30
    akhir
    0.28
    æľĢåIJİ
    0.27
    [last
    0.27
     ult
    0.26
    ç»Ī
    0.26
    =end
    0.26
    (last
    0.26
    finally
    0.25
    æľĢç»Ī
    0.25
    Activations Density 0.413%

    No Known Activations