© 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. 15892
    Prev
    Next
    INDEX
    Explanations

    stores, sent, jet, ice

    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
    çīĿ
    -0.21
     uLocal
    -0.19
    æŁĶåĴĮ
    -0.19
    é£İ鼨
    -0.19
    éĴĵ
    -0.19
    å¹½é»ĺ
    -0.19
    çIJĥåľº
    -0.18
     hton
    -0.18
    _Register
    -0.18
    YPD
    -0.18
    POSITIVE LOGITS
    æī¹æ¬¡
    0.33
    ä¸Ģæī¹
    0.26
    åıijè´§
    0.26
    导èĩ´
    0.25
    çĸijä¼¼
    0.24
    åı¯èĥ½å¯¼èĩ´
    0.24
    å¼ķåıij
    0.24
    严éĩįå½±åĵį
    0.24
    å«Įçĸij
    0.23
    ä¾ĽåºĶ
    0.23
    Activations Density 0.029%

    No Known Activations