© 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. 11667
    Prev
    Next
    INDEX
    Explanations

    killed, slain, witnessed, owed

    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
    press
    -0.22
    linger
    -0.18
    æįİ
    -0.18
    æĮīä¸ĭ
    -0.18
    åıĺåİĭ
    -0.18
    qu
    -0.18
    logen
    -0.17
    æ¸Ĺ
    -0.17
     labelText
    -0.17
    æ°©
    -0.17
    POSITIVE LOGITS
    ENN
    0.23
    äº
    0.20
    _controller
    0.20
    ÑĢин
    0.20
    驳
    0.20
    ä¸İåħ¶
    0.19
    åĽ
    0.19
    -angular
    0.19
    ENDED
    0.19
    èĩªåįij
    0.19
    Activations Density 0.188%

    No Known Activations