© 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. 2692
    Prev
    Next
    INDEX
    Explanations

    ending or departure

    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
    itol
    -0.25
    æĿĢ人
    -0.25
     lyn
    -0.23
    omal
    -0.23
    è¡Ħ
    -0.23
    éĩİçĶŁ
    -0.22
    nown
    -0.22
     midd
    -0.22
    nap
    -0.21
     Bieber
    -0.21
    POSITIVE LOGITS
     farewell
    0.32
    åĩºåı£
    0.31
    æĮ½
    0.31
    åijĬåĪ«
    0.30
    æīĵåĮħ
    0.29
     departure
    0.28
     goodbye
    0.26
     Export
    0.26
     Exit
    0.26
     depart
    0.26
    Activations Density 0.200%

    No Known Activations