© 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. 16110
    Prev
    Next
    INDEX
    Explanations

    of which

    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
    棵æłij
    -0.19
    åħ¢
    -0.19
    _MC
    -0.19
    addGroup
    -0.18
    adow
    -0.18
    çĩł
    -0.18
    è¾ķ
    -0.18
     Agricult
    -0.18
     Jeb
    -0.18
    磮
    -0.17
    POSITIVE LOGITS
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.31
     davon
    0.29
    åħ¶ä¸Ń
    0.28
     ones
    0.28
    åħ¶ä¸Ńæľī
    0.26
     thereof
    0.25
     ÙħÙĨÙĩا
    0.24
    对åħ¶è¿Ľè¡Į
    0.22
     ÙħÙĨÙĩÙħ
    0.21
    æĺİç¡®
    0.20
    Activations Density 0.156%

    No Known Activations