© 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. 13568
    Prev
    Next
    INDEX
    Explanations

    phone numbers and measurements

    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
    åĪĿäºĮ
    -0.21
    èĮ¬
    -0.21
     Ñ
    -0.20
    æݨ
    -0.19
    ⽬
    -0.18
    è¯įè¯Ń
    -0.17
    æ²Ļ
    -0.17
    è·Ŀ
    -0.17
     usur
    -0.17
    atched
    -0.17
    POSITIVE LOGITS
    ÑĤок
    0.20
    zza
    0.20
    åĪĨæĺİ
    0.19
    onomy
    0.18
    åįĥæĸ¹
    0.18
    èĩªä¸»åĵģçīĮ
    0.17
    ળ
    0.17
    geb
    0.17
    寤
    0.17
    è¯Ķ
    0.17
    Activations Density 0.010%

    No Known Activations