© 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. 14615
    Prev
    Next
    INDEX
    Explanations

    children and girls

    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
    åĮĻ
    -0.23
    ç»Ļå®Ŀå®Ŀ
    -0.23
    对åŃ©åŃIJ
    -0.20
    湫
    -0.19
    赢家
    -0.19
    å±IJ
    -0.19
    åħįè´£
    -0.18
    èĢģå¦Ī
    -0.18
    iki
    -0.18
    家éĥ½çŁ¥éģĵ
    -0.18
    POSITIVE LOGITS
    æįĭ
    0.21
    循
    0.20
    åIJĦ级
    0.20
    arness
    0.19
    shaw
    0.19
    bigint
    0.18
    çªŁ
    0.18
     ge
    0.18
     Americas
    0.18
    orpor
    0.18
    Activations Density 0.013%

    No Known Activations