© 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. 1168
    Prev
    Next
    INDEX
    Explanations

    obvious or trivial

    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
     Intern
    -0.24
    ä¼łæĿ¥
    -0.24
    æŃ£å¥½
    -0.24
     Silent
    -0.23
    -render
    -0.23
     silent
    -0.23
    æģ°å¥½
    -0.23
    posit
    -0.23
     Strict
    -0.22
    åıĬæŶ
    -0.22
    POSITIVE LOGITS
     obvious
    0.40
     straightforward
    0.33
     intuit
    0.31
     logically
    0.30
     plainly
    0.28
     obviously
    0.28
    /basic
    0.27
    ãĤıãģĭãĤĭ
    0.27
    缴è§Ĥ
    0.27
    /simple
    0.27
    Activations Density 0.072%

    No Known Activations