© 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. 14098
    Prev
    Next
    INDEX
    Explanations

    snakes or ID

    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
    gó
    -0.21
    éĿ¢ä¸Ĭ
    -0.20
    è¨Ģè¡Į
    -0.20
    endale
    -0.19
    åĽŀæĥ³
    -0.19
    ippy
    -0.19
    æ²»
    -0.18
    NSS
    -0.18
    è´¡çĮ®
    -0.17
    å¨ĩ
    -0.17
    POSITIVE LOGITS
    çѵ
    0.19
    çĻ»ä¸Ĭ
    0.18
     coils
    0.18
    å¸Ń
    0.18
    æī©å¼ł
    0.17
    ä¹ĭå¤ľ
    0.17
     trÆ°Æ¡ng
    0.17
    èļº
    0.17
    ARAM
    0.17
    avid
    0.16
    Activations Density 0.006%

    No Known Activations