© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    symbol sequences

    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
     McCartney
    -0.26
    å¾Īåĸľæ¬¢
    -0.23
    âĹ»
    -0.23
    .fhir
    -0.21
     Benef
    -0.21
    culos
    -0.21
    Tracks
    -0.20
    adesh
    -0.20
    å¿į
    -0.20
     rival
    -0.20
    POSITIVE LOGITS
    ä»ħä¾Ľ
    0.23
    å®īæİĴ
    0.21
    çľ¼æ³ª
    0.21
    æĪijè¦ģ
    0.21
     infos
    0.21
    æĪijæĺ¯
    0.21
    äººæł¼
    0.20
    ä¸įå®Į
    0.20
    ä¸¥æł¼
    0.20
    æ¥Ķ
    0.20
    Activations Density 0.065%

    No Known Activations