© 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. 720
    Prev
    Next
    INDEX
    Explanations

    award winners or nominees

    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
     warns
    -0.22
    nda
    -0.21
    acin
    -0.21
     warnings
    -0.20
    ød
    -0.20
     Estimate
    -0.20
    _WARN
    -0.20
    èµ·æĿ¥
    -0.20
     ensl
    -0.20
    ANDLE
    -0.20
    POSITIVE LOGITS
    åIJįåįķ
    0.30
    åĪĨåĪ«æĺ¯
    0.30
    åĩºçĤī
    0.26
     deserving
    0.26
    ç²īä¸Ŀ
    0.25
    site
    0.24
    æĪIJåijĺ
    0.24
    lists
    0.23
    åħ¬å¸ĥ
    0.23
    -list
    0.23
    Activations Density 0.020%

    No Known Activations