© 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. 11218
    Prev
    Next
    INDEX
    Explanations

    super contributions, asset protection

    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
    åĬ¡
    -0.23
    åħ¨å±Ģ
    -0.21
    ÑĢай
    -0.21
    æīĭæĦŁ
    -0.21
    (Arg
    -0.20
    -orders
    -0.20
    åįĵè¶Ĭ
    -0.19
    (Order
    -0.19
    æĪIJçĨŁ
    -0.19
    èĬ±çº¹
    -0.19
    POSITIVE LOGITS
    èıı
    0.22
    æ°¸ä¹ħ
    0.21
    /bl
    0.21
    æī©å®¹
    0.21
    åIJŀ
    0.20
    IGH
    0.20
    eland
    0.20
    è¶ħæłĩ
    0.20
    éĻIJéĩı
    0.19
    è±ģ
    0.19
    Activations Density 0.008%

    No Known Activations