© 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. 15077
    Prev
    Next
    INDEX
    Explanations

    tech hardware and gadget reviews

    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
    Pinterest
    -0.23
     paperwork
    -0.22
     Pinterest
    -0.21
    è±Ĩçĵ£
    -0.20
    Cour
    -0.18
    storybook
    -0.18
     spotify
    -0.18
    ç§ijå°Ķ
    -0.18
    æ¹ĸ
    -0.18
    uvw
    -0.18
    POSITIVE LOGITS
    è¯Ħæµĭ
    0.37
    çĶ¨æĪ·ä½ĵéªĮ
    0.28
    æµĭè¯Ħ
    0.26
    硬件
    0.25
    ç±³ç²ī
    0.25
    æ¡ĮéĿ¢
    0.24
    æĶ»åĩ»
    0.24
     Hardware
    0.24
    æ¶Īè´¹
    0.24
     hardware
    0.24
    Activations Density 0.036%

    No Known Activations