© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16587
    Prev
    Next
    INDEX
    Explanations

    of [noun]

    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
    ä¸Ģæĸ¹
    -0.22
    ä¸Ģå¹ħ
    -0.20
     breeds
    -0.20
    ä¸Ģæł¹
    -0.20
    è¿ĻåĿĹ
    -0.19
    ä¸Ģèīĺ
    -0.19
     authority
    -0.19
    nuts
    -0.18
    ä¸Ģè¾Ĩ
    -0.18
     place
    -0.17
    POSITIVE LOGITS
    adden
    0.19
    çļĦæĹ¥åŃIJéĩĮ
    0.19
    é²°
    0.19
    åħ¨æµģç¨ĭ
    0.19
    ancell
    0.19
    uxe
    0.18
    ienie
    0.18
    æīĵçĿĢ
    0.18
    ackle
    0.18
    éĴ¦
    0.18
    Activations Density 0.033%

    No Known Activations