© 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. 13120
    Prev
    Next
    INDEX
    Explanations

    importing files or data

    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
    ippers
    -0.21
    /slick
    -0.21
    bir
    -0.20
    ammers
    -0.19
    OptionsResolver
    -0.18
    á»įng
    -0.18
    ppe
    -0.18
    CallableWrapper
    -0.18
    bjerg
    -0.18
    XHR
    -0.17
    POSITIVE LOGITS
    è¿ĽæĿ¥
    0.34
    into
    0.27
     vÃło
    0.25
    è¿Ľåİ»
    0.24
    Into
    0.24
     into
    0.24
    /import
    0.24
    å¤ĸéĥ¨
    0.22
    导åħ¥
    0.22
    FromFile
    0.21
    Activations Density 0.066%

    No Known Activations