© 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. 15981
    Prev
    Next
    INDEX
    Explanations

    sent with destination

    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
    æĥħ人
    -0.21
    åħ¶æīĢ
    -0.20
    æį§
    -0.19
    è¿ŀ线
    -0.18
    çľĭä»ĸ
    -0.17
    æĢĿ念
    -0.17
    견
    -0.17
    áĢĵ
    -0.17
    åīģ
    -0.17
    å¿ĥæĢĿ
    -0.17
    POSITIVE LOGITS
    aits
    0.20
    ties
    0.18
    mgr
    0.18
    ä½łæĺ¯
    0.17
     Quart
    0.17
    urm
    0.17
    scriptions
    0.17
    à¸Ńà¸Ńà¸ģà¹Ħà¸Ľ
    0.17
     refinery
    0.17
     quadrant
    0.17
    Activations Density 0.011%

    No Known Activations