© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    served as

    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
    oref
    -0.28
    梦è§ģ
    -0.23
    ä¼ĹæīĢ
    -0.23
    ç»ıéªĮåĴĮ
    -0.23
    åĴ«
    -0.23
    çİĭèĢħ
    -0.23
    amus
    -0.22
     aliens
    -0.22
    éĨĴäºĨ
    -0.22
    渲
    -0.21
    POSITIVE LOGITS
    onde
    0.25
    azzo
    0.24
    为æŃ¢
    0.24
    lets
    0.23
    æķ´æķ´
    0.23
    ongo
    0.22
    åĪļ好
    0.22
    åĨįåĪ°
    0.22
    å·¦åı³
    0.22
    ä¹ĭéĹ´
    0.21
    Activations Density 0.076%

    No Known Activations