© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15143
    Prev
    Next
    INDEX
    Explanations

    enter information

    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
    ecess
    -0.20
    ä¼łåªĴ
    -0.19
    ør
    -0.19
     Colomb
    -0.19
    stell
    -0.18
    æ®ĥ
    -0.18
    illa
    -0.17
    /latest
    -0.17
     Certification
    -0.17
    áo
    -0.17
    POSITIVE LOGITS
    è¿Ľåİ»
    0.32
     into
    0.25
    into
    0.23
    Into
    0.22
    åĪ°è¿ĻéĩĮ
    0.20
    OrUpdate
    0.20
    å¾Ĺåĩº
    0.19
    ãĥ¥ãĥ¼
    0.19
     backwards
    0.19
     vÃło
    0.19
    Activations Density 0.065%

    No Known Activations