© 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. 16318
    Prev
    Next
    INDEX
    Explanations

    names after 'Don', 'Viv', 'Rich', 'Has', 'Math', 'V', 'De'

    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
    ifest
    -0.21
    há»ķ
    -0.20
    -the
    -0.20
    ften
    -0.18
    szed
    -0.18
    põe
    -0.18
    ä¸Ģæīĭ
    -0.18
     Mast
    -0.18
    wik
    -0.18
    restrial
    -0.18
    POSITIVE LOGITS
    çł£
    0.23
    误ä¼ļ
    0.23
    åŃIJéĩĮ
    0.23
    åĮ»æĬ¤
    0.21
    èĸ¯
    0.20
    èĪ«
    0.19
    佬
    0.19
    å§ij
    0.19
    åĬĽè¿ĺæĺ¯
    0.19
    æŃī
    0.18
    Activations Density 0.092%

    No Known Activations