© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    distance units

    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
    åį³ä½¿æĺ¯
    -0.28
    ä¿Ŀåħ»
    -0.24
    achievement
    -0.23
    Desk
    -0.23
    ä¸Ģç§Ĵ
    -0.22
    çIJĨ解åĴĮ
    -0.21
    马æĿ¥è¥¿äºļ
    -0.21
    ä¸ĩä¸Ģ
    -0.21
    èĪªç©ºåħ¬åı¸
    -0.21
    vac
    -0.21
    POSITIVE LOGITS
    -long
    0.35
     distance
    0.32
    -radius
    0.28
     inland
    0.28
    çļĦè·Ŀ离
    0.28
    -distance
    0.28
     drifted
    0.28
    å¾ĴæŃ¥
    0.28
     radius
    0.27
     fence
    0.26
    Activations Density 0.024%

    No Known Activations