© 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. 2681
    Prev
    Next
    INDEX
    Explanations

    numbers and delimiters

    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
    aland
    -0.24
    arti
    -0.22
    CAPE
    -0.22
     qu
    -0.21
    —he
    -0.21
    èĤ¢
    -0.20
     pan
    -0.20
    ez
    -0.20
    utter
    -0.20
    Bindings
    -0.20
    POSITIVE LOGITS
    omy
    0.24
    edException
    0.22
    washer
    0.21
    ä½İä¼°
    0.21
    /object
    0.21
     Ru
    0.21
    缺
    0.21
    ary
    0.21
     Including
    0.21
    shade
    0.21
    Activations Density 0.117%

    No Known Activations