© 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. 485
    Prev
    Next
    INDEX
    Explanations

    If then

    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
    çŃ¹çłģ
    -0.24
    chal
    -0.23
    çŃĸ
    -0.22
    ç§ijæķĻ
    -0.22
    ften
    -0.22
    often
    -0.21
    ÑģÑĤанов
    -0.21
    è¿Ļç±»
    -0.21
     visceral
    -0.21
    -standard
    -0.21
    POSITIVE LOGITS
    è¿Ŀåıį
    0.27
    äºī
    0.25
     disputes
    0.24
     misunderstand
    0.24
    误
    0.24
     disagreements
    0.24
     cler
    0.24
    åıĺæĽ´
    0.23
     erroneous
    0.23
     contacting
    0.23
    Activations Density 0.019%

    No Known Activations