© 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. 12740
    Prev
    Next
    INDEX
    Explanations

    numbers after `-run`

    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
    人äºĭ
    -0.21
    çĶ¸
    -0.20
    äºĭåĬ¡
    -0.20
    /Public
    -0.20
     ÐIJлекÑģан
    -0.19
    ä¸Ĭå¹´
    -0.19
     Roch
    -0.19
    еÑģÑĤеÑģÑĤвенн
    -0.19
    æ³ħ
    -0.19
    åŁ´
    -0.18
    POSITIVE LOGITS
    æģŃ
    0.25
    èĿĩ
    0.20
    åĢĴå¡Į
    0.20
     kı
    0.19
    对åѦçĶŁ
    0.19
    äºĴèģĶäºĴéĢļ
    0.19
    BOT
    0.18
    çĸijä¼¼
    0.18
    缸éĢļ
    0.18
    å¿ĺè®°äºĨ
    0.18
    Activations Density 0.010%

    No Known Activations