© 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. 2870
    Prev
    Next
    INDEX
    Explanations

    care services

    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
    çĭ¡
    -0.24
    éĺ´å½±
    -0.23
     Success
    -0.23
    çŁ¥å·±
    -0.23
    success
    -0.22
    submission
    -0.22
    Known
    -0.22
    æ³ķåħ°
    -0.22
    人å¿ĥ
    -0.22
     CEO
    -0.21
    POSITIVE LOGITS
     services
    0.34
    åĮ»çĸĹæľįåĬ¡
    0.32
     chÄĥm
    0.32
    çĽijæĬ¤
    0.31
     care
    0.30
    æķijæ²»
    0.29
    çħ§æĸĻ
    0.29
    å¿ħè¦ģçļĦ
    0.28
    æľįåĬ¡
    0.27
     personalised
    0.27
    Activations Density 0.096%

    No Known Activations