© 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. 1232
    Prev
    Next
    INDEX
    Explanations

    shapes, lines, and colors

    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
    mind
    -0.26
    åĥıæĺ¯
    -0.25
    å¤ļ
    -0.25
     mind
    -0.24
    å±ĢéĿ¢
    -0.24
    finalize
    -0.24
    Mind
    -0.23
     Mind
    -0.22
    _business
    -0.22
     minds
    -0.22
    POSITIVE LOGITS
     highlighted
    0.31
    éĺ´å½±
    0.31
    åĪĨåĪ«ä¸º
    0.29
     arrows
    0.28
     circles
    0.28
     lightly
    0.28
     arrow
    0.27
     overlay
    0.27
     overl
    0.27
     shown
    0.27
    Activations Density 0.047%

    No Known Activations