© 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. 2534
    Prev
    Next
    INDEX
    Explanations

    only followed by a singular entity

    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
    满满
    -0.30
    满满çļĦ
    -0.24
    ital
    -0.23
    èĢģé¾ĦåĮĸ
    -0.23
    åIJĦèĩªçļĦ
    -0.22
    ãģ¤ãģį
    -0.22
    æĸ°å¸¸æĢģ
    -0.22
    æĢ»å±Ģ
    -0.21
     \@
    -0.21
    æĢ»éĩı
    -0.21
    POSITIVE LOGITS
     thing
    0.29
    åĬŀæ³ķ
    0.28
    thing
    0.28
     ones
    0.28
    tons
    0.27
    åĦ¿
    0.26
    -than
    0.25
     instance
    0.25
     ways
    0.24
     kinds
    0.24
    Activations Density 0.016%

    No Known Activations