© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15013
    Prev
    Next
    INDEX
    Explanations

    detection and sensing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    飬
    -0.21
    æŶè£ħ
    -0.20
    CHEDULE
    -0.20
    éĢĶå¾Ħ
    -0.19
    æĸ°è½¦
    -0.19
    _Renderer
    -0.19
    witter
    -0.18
    amil
    -0.18
    ç»
    -0.18
    æĮĤ
    -0.18
    POSITIVE LOGITS
    æĦŁåºĶ
    0.39
     detection
    0.33
     detecting
    0.33
    ä¼łæĦŁ
    0.33
    æ£Ģæµĭ
    0.31
    è¯ĨåĪ«
    0.31
    Detection
    0.30
    æįķæįī
    0.30
     Detection
    0.29
     detects
    0.28
    Activations Density 0.324%

    No Known Activations