© 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. 13665
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    roy
    -0.22
     Hag
    -0.21
    gu
    -0.21
    è¹ĭ
    -0.20
    èµ·
    -0.20
    ially
    -0.19
     Fif
    -0.19
    ç¥ŀä»Ļ
    -0.18
    enary
    -0.18
    èĩŃ
    -0.18
    POSITIVE LOGITS
    uum
    0.23
    æĪIJ人
    0.19
    æĿ¥çĶµ
    0.19
    ndo
    0.19
    ä¸įåľ¨
    0.19
    èĭ¦èĭ¦
    0.18
    vak
    0.18
    使人
    0.18
    _variance
    0.18
    äºĭä¸ļéĥ¨
    0.18
    Activations Density 0.039%

    No Known Activations