© 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. 2325
    Prev
    Next
    INDEX
    Explanations

    week of, week long, weekly

    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
    áŀĤ
    -0.21
    resco
    -0.19
    ../
    -0.18
    åĥŃ
    -0.18
    inea
    -0.18
    -Sah
    -0.18
    èĮģ
    -0.17
    umeric
    -0.17
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.17
     widely
    -0.17
    POSITIVE LOGITS
    /month
    0.49
    -long
    0.34
    lies
    0.31
    abouts
    0.27
    night
    0.27
     lá»ħ
    0.26
    days
    0.26
    ä¹ĭåĨħ
    0.26
    åĨħçļĦ
    0.24
     atrás
    0.24
    Activations Density 0.066%

    No Known Activations