© 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. 1994
    Prev
    Next
    INDEX
    Explanations

    Professor of academic subjects

    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
    æ¡ĥèĬ±
    -0.23
    azaar
    -0.23
    orm
    -0.22
    åIJĦèĩªçļĦ
    -0.22
    åĬ¨æīĭ
    -0.22
    quis
    -0.22
    线ä¸ĭ
    -0.22
    è±ĨæµĨ
    -0.22
     anyways
    -0.22
    èł¢
    -0.22
    POSITIVE LOGITS
     specializing
    0.28
     honorary
    0.28
    åľ¨ç¾İåĽ½
    0.26
     internationally
    0.26
     Teaching
    0.26
    åī¯æķĻæİĪ
    0.25
    åħ¼ä»»
    0.25
     teaches
    0.25
     origin
    0.25
     unconditional
    0.25
    Activations Density 0.045%

    No Known Activations