© 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. 12095
    Prev
    Next
    INDEX
    Explanations

    prepare to tell

    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
    ä»įåľ¨
    -0.22
    èĭ¦
    -0.22
    姨
    -0.22
     Pike
    -0.20
    Reject
    -0.20
    æĢħ
    -0.19
    UR
    -0.19
     моделÑĮ
    -0.19
    USH
    -0.19
    é³Ŀ
    -0.19
    POSITIVE LOGITS
    èѦåijĬ
    0.24
    åľ¨æĪij
    0.24
    ãĤ¬ãĤ¤
    0.23
    æĮijè¡ħ
    0.23
    对æĪij
    0.22
    arus
    0.21
    è§Ħç¨ĭ
    0.20
    æ³ķå¾ĭ责任
    0.20
    è§Ħ
    0.19
    éĹ®è´£
    0.19
    Activations Density 0.046%

    No Known Activations