© 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. 13385
    Prev
    Next
    INDEX
    Explanations

    sorry, can, how, this, please, reading

    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¸Ĭä¸ĭ
    -0.24
    Registry
    -0.20
    è¿Ļ段
    -0.19
    ize
    -0.19
    ä¾ĭ
    -0.18
    icals
    -0.17
    æĸĩåŃĹ
    -0.17
    t
    -0.17
    changes
    -0.17
    Ctx
    -0.17
    POSITIVE LOGITS
     principalColumn
    0.21
    thren
    0.20
     iNdEx
    0.19
    _alive
    0.19
    	TokenName
    0.18
    ecess
    0.18
    æ¶Ķ
    0.18
     buz
    0.18
    æѧè§Ĩ
    0.18
    hek
    0.18
    Activations Density 0.186%

    No Known Activations