© 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. 1730
    Prev
    Next
    INDEX
    Explanations

    continue to

    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
    è¦ģæĥ³
    -0.25
    ç»ĵæŀľ
    -0.23
    ierz
    -0.22
    rador
    -0.22
    egov
    -0.22
    离ä¸įå¼Ģ
    -0.21
     Earn
    -0.21
    earned
    -0.21
    amy
    -0.21
    æĺİç¡®
    -0.21
    POSITIVE LOGITS
    ä¸ĭåİ»
    0.29
    èµ°ä¸ĭåİ»
    0.27
     smoothly
    0.26
     continuation
    0.24
    ç»Ń
    0.23
     immediately
    0.22
    åıĻ
    0.22
     proceed
    0.22
     Suddenly
    0.21
     abruptly
    0.21
    Activations Density 0.021%

    No Known Activations