© 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. 2734
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
     tab
    -0.29
     log
    -0.26
    uto
    -0.25
    è¾ķ
    -0.25
     inf
    -0.24
    tab
    -0.23
    put
    -0.23
    PUT
    -0.23
    åĽł
    -0.23
    æīĺ
    -0.23
    POSITIVE LOGITS
    -Cs
    0.25
    licht
    0.24
    PAL
    0.24
    edly
    0.23
     RENDER
    0.23
     Vocal
    0.23
     Encrypt
    0.23
     molest
    0.23
     Pron
    0.22
    >{"
    0.22
    Activations Density 0.023%

    No Known Activations