© 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. 13818
    Prev
    Next
    INDEX
    Explanations

    alternatively or otherwise

    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
    æĪĸåħ¶ä»ĸ
    -0.20
    æĪĸèĢħåħ¶ä»ĸ
    -0.20
    à¹ĥส
    -0.19
    aan
    -0.19
    ResponseBody
    -0.19
    èģĶåIJĪåĽ½
    -0.18
    ä¸ĩåįĥ
    -0.18
    æŃ£ãģĹãģĦ
    -0.18
    è¦ĭãģŁ
    -0.18
    çĤ¹äº®
    -0.17
    POSITIVE LOGITS
    thon
    0.31
     alternatively
    0.29
     otherwise
    0.23
    acles
    0.23
    agn
    0.23
    èĩ³å°ij
    0.21
    ignal
    0.21
     Pow
    0.21
    å¹²èĦĨ
    0.21
    ign
    0.21
    Activations Density 0.114%

    No Known Activations