© 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. 16111
    Prev
    Next
    INDEX
    Explanations

    taking, trying, working, having, been

    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
    çĽ¼
    -0.19
    象
    -0.19
    éĢıæĺİ
    -0.18
    fax
    -0.18
    åħ¶æ¬¡
    -0.18
    cow
    -0.17
    uper
    -0.17
    ilk
    -0.17
    Convention
    -0.17
     Ferrari
    -0.17
    POSITIVE LOGITS
    åIJįåı«
    0.23
    æĢ¥éľĢ
    0.21
    éģĩè§ģ
    0.21
    æĥ³çŁ¥éģĵ
    0.20
    çĭŃçªĦ
    0.20
     ÑģлÑĥÑĩай
    0.20
    亲æĪļ
    0.20
    éģĩåĪ°äºĨ
    0.19
    éľĢè¦ģ
    0.19
    åħ»
    0.19
    Activations Density 1.194%

    No Known Activations