© 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. 2157
    Prev
    Next
    INDEX
    Explanations

    citation prefixes

    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
    /li
    -0.24
     SOAP
    -0.24
    åĭ¿
    -0.23
    ski
    -0.23
     kinda
    -0.23
    åı¯è§Ĩ
    -0.23
     hopes
    -0.22
     pretty
    -0.22
    sem
    -0.22
    åĵŃæ³£
    -0.21
    POSITIVE LOGITS
    åĢĴ
    0.29
    inder
    0.25
    è¦ģéĹ»
    0.23
     ìĿ¸
    0.23
    inton
    0.22
    äºĮæĺ¯
    0.22
    undra
    0.22
    ooter
    0.22
    èµ·
    0.22
     Bundy
    0.22
    Activations Density 0.096%

    No Known Activations