© 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. 15785
    Prev
    Next
    INDEX
    Explanations

    graduated with degree or bachelor

    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
    笼
    -0.23
     outside
    -0.22
    æIJģ
    -0.21
     by
    -0.19
    æ²ĥå°Ķ
    -0.19
    .callback
    -0.18
     dou
    -0.18
    æī¹ç¤º
    -0.18
     Dont
    -0.18
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.18
    POSITIVE LOGITS
    åĩºåĵģ
    0.23
    è´¢åĬ¡ç®¡çIJĨ
    0.19
    éĩįçĤ¹é¢ĨåŁŁ
    0.19
    åİŁä»¶
    0.18
    产ä¸ļåıijå±ķ
    0.18
    uran
    0.18
    年产
    0.18
    æ²Ķ
    0.17
    _lhs
    0.17
    ä¸Ģ群
    0.17
    Activations Density 0.028%

    No Known Activations