© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 861
    Prev
    Next
    INDEX
    Explanations

    machine and its purpose

    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
    ģ
    -0.21
    rious
    -0.21
     cáo
    -0.20
    çİ°å®ŀä¸Ń
    -0.19
    ERS
    -0.19
     ë¶Ī구íķĺê³ł
    -0.19
    imensional
    -0.18
    tech
    -0.18
    æķ¬ä¸ļ
    -0.18
    ITIVE
    -0.18
    POSITIVE LOGITS
    hood
    0.31
     móc
    0.28
    -readable
    0.27
    yard
    0.27
    ette
    0.26
    yards
    0.24
    -fluid
    0.24
    ered
    0.24
    yar
    0.23
    e
    0.22
    Activations Density 0.029%

    No Known Activations