© 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. 1703
    Prev
    Next
    INDEX
    Explanations

    personal and residential use

    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
    lösung
    -0.23
    åŁĴ
    -0.22
    ssi
    -0.22
     Chapman
    -0.22
    repid
    -0.21
    ASTE
    -0.21
    æĵ¬
    -0.21
    åķ¸
    -0.21
    åħ¬ç¤º
    -0.21
    åŀĽ
    -0.20
    POSITIVE LOGITS
    æ°ijçĶ¨
    0.32
    个人
    0.29
    /business
    0.27
    åķĨçĶ¨
    0.26
     residential
    0.26
     Leisure
    0.26
    ä½ıå®ħ
    0.26
     consumer
    0.25
     academics
    0.25
    åıĬ
    0.24
    Activations Density 0.305%

    No Known Activations