© 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. 12668
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code structures

    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
    ETO
    -0.20
    bul
    -0.20
    bio
    -0.19
    令
    -0.19
    Rel
    -0.19
     area
    -0.19
    .cid
    -0.19
     Dome
    -0.19
    íĹĢ
    -0.18
    roller
    -0.18
    POSITIVE LOGITS
    FunctionFlags
    0.25
    webElementProperties
    0.24
    äºĶå®ĺ
    0.24
    /WebAPI
    0.23
    å°ıåŃIJ
    0.23
    	TokenName
    0.22
    å±Ĥåĩºä¸į
    0.22
    ableOpacity
    0.22
    åIJĦè¡ĮåIJĦ
    0.21
    èIJ¥ä¸ļæī§
    0.21
    Activations Density 0.149%

    No Known Activations