© 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. 12678
    Prev
    Next
    INDEX
    Explanations

    restoration or restored

    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
    elen
    -0.23
    åŃIJéĩĮ
    -0.22
    -0.20
    åįģ足
    -0.20
    ster
    -0.19
    eral
    -0.18
    eline
    -0.17
    å²ĺ
    -0.17
    anners
    -0.17
    nels
    -0.17
    POSITIVE LOGITS
    OrUpdate
    0.21
    ä¸İåıijå±ķ
    0.20
    åĴĮåıijå±ķ
    0.19
    å®Įæ¯ķ
    0.18
    å·¥ä½ľçļĦ
    0.18
    ors
    0.17
    orld
    0.17
    æĢ§çĸ¾çĹħ
    0.17
    ists
    0.17
    /ref
    0.17
    Activations Density 0.021%

    No Known Activations