© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 258
    Prev
    Next
    INDEX
    Explanations

    typhoon, tycoon, Tywin, Tyrol, Tytin

    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
    ãģĵãģ¨
    -0.23
    s
    -0.20
    ertz
    -0.19
    sı
    -0.18
    pressed
    -0.18
    hin
    -0.18
     dozen
    -0.17
    äºĭåĦ¿
    -0.17
    ness
    -0.17
    ThreadId
    -0.17
    POSITIVE LOGITS
    ahead
    0.26
    ess
    0.25
    ëį°
    0.24
    ../
    0.23
    ologies
    0.22
    phoon
    0.22
     ë¶Ī구íķĺê³ł
    0.21
    adic
    0.20
    ably
    0.20
    burgh
    0.20
    Activations Density 0.028%

    No Known Activations