© 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. 16463
    Prev
    Next
    INDEX
    Explanations

    geographical entities and technical terms

    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
    touches
    -0.20
    æĬµ
    -0.20
    åIJĥåĪ°
    -0.19
    _lbl
    -0.19
    æıŃæĻĵ
    -0.18
    æŁĦ
    -0.18
     ÑģоÑģÑĤоÑıнии
    -0.18
    WSC
    -0.18
    enen
    -0.17
    vice
    -0.17
    POSITIVE LOGITS
    åĴĮåħ¶ä»ĸ
    0.28
    ä¸Ģæł·
    0.28
    åIJĮæľŁ
    0.28
    æĪĸåħ¶ä»ĸ
    0.28
    ä¸Ģæł·çļĦ
    0.25
    åIJĮæł·
    0.24
     similarly
    0.23
    çŃī人
    0.23
     counterparts
    0.23
     gibi
    0.22
    Activations Density 0.192%

    No Known Activations