© 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. 2282
    Prev
    Next
    INDEX
    Explanations

    preliminary drawings and outlines

    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
    ä¸ĩæĪ·
    -0.24
    -enabled
    -0.24
    éĢ¢
    -0.23
     enrol
    -0.23
     laboratories
    -0.22
    åıĹéĻIJ
    -0.22
    nore
    -0.22
     enrollment
    -0.21
    éĢļè¡Į
    -0.21
    Licensed
    -0.21
    POSITIVE LOGITS
     sketches
    0.40
     sketch
    0.38
     outline
    0.37
     rough
    0.37
    æľĢåĪĿçļĦ
    0.36
    éĺ¶æ®µ
    0.35
     outlines
    0.35
    æŀĦæĢĿ
    0.34
     preliminary
    0.34
    åĪĿæŃ¥
    0.33
    Activations Density 0.027%

    No Known Activations