© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12648
    Prev
    Next
    INDEX
    Explanations

    VC, Hybrid, stealth, touchscreen

    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
    pins
    -0.20
    è´¯
    -0.20
    .ib
    -0.19
    ouch
    -0.19
    ly
    -0.19
    _python
    -0.18
    ä¸į代表
    -0.18
    och
    -0.18
    åīįæĸ¹
    -0.18
    çļĦ帮åĬ©
    -0.18
    POSITIVE LOGITS
    éļIJç§ģ
    0.18
     Apprent
    0.18
     handjob
    0.18
    á¸ĭ
    0.18
    å°±åĮ»
    0.18
    epam
    0.18
     Adults
    0.17
     Revised
    0.17
     Patrol
    0.17
    etsk
    0.17
    Activations Density 0.070%

    No Known Activations