© 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. 16087
    Prev
    Next
    INDEX
    Explanations

    code exports

    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
     моÑīн
    -0.19
    á¹
    -0.18
     ÐĶмиÑĤÑĢ
    -0.18
    æ²ī
    -0.18
    è¦ĥ
    -0.18
     ÐŁÐ¾Ñĩем
    -0.18
     HOLDERS
    -0.17
    éĤµ
    -0.17
     miners
    -0.17
     пÑĥÑĤеÑĪ
    -0.17
    POSITIVE LOGITS
    è´ŁéĿ¢
    0.19
    ä¹Įåħĭåħ°
    0.19
     пок
    0.18
    鬼
    0.18
     everlasting
    0.18
    opcode
    0.18
    äº
    0.18
    ä¾ĽåºĶéĵ¾
    0.17
    linkplain
    0.17
    /material
    0.17
    Activations Density 0.005%

    No Known Activations