© 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. 126
    Prev
    Next
    INDEX
    Explanations

    immediate situations/events

    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
    åĿļæĮģä¸įæĩĪ
    -0.23
    suming
    -0.23
    åĵ¡
    -0.22
    ever
    -0.22
    spiel
    -0.21
    ning
    -0.21
    ous
    -0.21
    itionally
    -0.21
    å¾Ĺèµ·
    -0.20
    enton
    -0.20
    POSITIVE LOGITS
     vicinity
    0.25
    aney
    0.24
    aneously
    0.23
    yat
    0.22
    LY
    0.21
    ioned
    0.21
     threats
    0.20
    æĿ¥è®²
    0.20
    cgi
    0.20
     tense
    0.20
    Activations Density 0.009%

    No Known Activations