© 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. 2011
    Prev
    Next
    INDEX
    Explanations

    licenses links

    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
    oram
    -0.24
    oland
    -0.23
    éļıæŶéļıåľ°
    -0.23
    odem
    -0.22
    ernes
    -0.22
    stride
    -0.21
    éªĿ
    -0.21
    (moment
    -0.21
    OLOR
    -0.21
    令人
    -0.20
    POSITIVE LOGITS
     Losing
    0.22
     Accent
    0.21
     Towers
    0.21
    åIJĮäºĭ们
    0.21
    çİ
    0.21
    -answer
    0.21
     lá»Ĺi
    0.20
     KA
    0.20
    è°£
    0.20
     downloading
    0.20
    Activations Density 0.001%

    No Known Activations