© 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. 1315
    Prev
    Next
    INDEX
    Explanations

    Supreme Court

    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
    ting
    -0.23
    åĩĿèģļ
    -0.23
    æĴ
    -0.22
    æĢ»æľī
    -0.22
    ful
    -0.22
    åıĺå¹»
    -0.21
    tings
    -0.21
    даÑİÑĤ
    -0.21
     lots
    -0.21
    gin
    -0.21
    POSITIVE LOGITS
    éĺ¶æ®µæĢ§
    0.25
     Relax
    0.22
    óa
    0.22
    liga
    0.22
     overthrow
    0.21
     AAP
    0.21
    主åĬ¨æĢ§
    0.21
    æijĴ
    0.21
    éĥĬ
    0.21
     Crimes
    0.20
    Activations Density 0.005%

    No Known Activations