© 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. 2803
    Prev
    Next
    INDEX
    Explanations

    now

    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
    anchor
    -0.25
    snake
    -0.23
    yield
    -0.23
    ä¸įåĥı
    -0.23
     Downs
    -0.23
     anchor
    -0.23
    fresh
    -0.23
    weit
    -0.22
    ä¹Łä¸įéĶĻ
    -0.22
     Scores
    -0.22
    POSITIVE LOGITS
     now
    0.33
    çİ°åľ¨
    0.30
     retrospect
    0.28
     provisional
    0.28
     NOW
    0.25
    æ»ŀåIJİ
    0.25
    .asc
    0.24
    now
    0.24
    	now
    0.24
     Now
    0.24
    Activations Density 0.163%

    No Known Activations