© 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. 1415
    Prev
    Next
    INDEX
    Explanations

    Temple Grandin, CHARGE syndrome, Oliver Sacks

    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
    éħIJ
    -0.25
    leigh
    -0.24
    åľºä¸Ĭ
    -0.24
     newArray
    -0.23
    _intent
    -0.23
    .isArray
    -0.23
    æ²¹èĢĹ
    -0.23
    setId
    -0.22
    mono
    -0.22
    eco
    -0.22
    POSITIVE LOGITS
    磨
    0.24
    .windows
    0.24
    urd
    0.23
    Communic
    0.23
    AppBar
    0.22
     sensory
    0.22
     AppBar
    0.22
     window
    0.22
    èģĭ
    0.22
     gover
    0.22
    Activations Density 0.014%

    No Known Activations