© 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. 2453
    Prev
    Next
    INDEX
    Explanations

    under the terms

    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
    former
    -0.21
     дол
    -0.20
    lesia
    -0.19
     inset
    -0.19
    uary
    -0.19
    yar
    -0.19
    greg
    -0.19
    槿
    -0.19
     unloaded
    -0.18
    çİĸ
    -0.18
    POSITIVE LOGITS
    neath
    0.44
    lain
    0.34
    lining
    0.33
    stood
    0.33
    /out
    0.30
    represented
    0.29
    /by
    0.29
    whelming
    0.28
    lined
    0.28
    lies
    0.27
    Activations Density 0.157%

    No Known Activations