© 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. 548
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide or CO2

    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
    icular
    -0.21
    ä¸įåľ¨ä¹İ
    -0.21
    èĩĬ
    -0.21
    AGER
    -0.20
    é¢Ĩè¢ĸ
    -0.19
    ANO
    -0.19
    ä¹ĭä¸Ģ
    -0.19
    acie
    -0.19
    acies
    -0.19
    asi
    -0.19
    POSITIVE LOGITS
    -rich
    0.23
    ç¨İ
    0.23
    .gz
    0.23
     baths
    0.22
    ombs
    0.22
    为é¦ĸ
    0.21
    gre
    0.21
    ¼
    0.21
    elastic
    0.20
    /DD
    0.20
    Activations Density 0.025%

    No Known Activations