© 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. 2382
    Prev
    Next
    INDEX
    Explanations

    anticlimactic, disappointing, surprising

    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
     Weeks
    -0.26
    dings
    -0.25
    iors
    -0.24
     abl
    -0.23
     kra
    -0.23
    è±IJ
    -0.23
    å¥īçĮ®
    -0.22
     furn
    -0.22
    DS
    -0.22
    repid
    -0.22
    POSITIVE LOGITS
     complicated
    0.32
    å¤įæĿĤçļĦ
    0.29
     surprising
    0.28
    羣缸
    0.28
     disappointing
    0.28
    å¤įæĿĤ
    0.28
     disappoint
    0.28
     simpler
    0.28
    羣å®ŀ
    0.27
     reality
    0.27
    Activations Density 0.080%

    No Known Activations