© 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. 13623
    Prev
    Next
    INDEX
    Explanations

    speaker components

    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
    社ä¼ļåıijå±ķ
    -0.21
    åĪĩ
    -0.21
    .chain
    -0.21
    éĵ¾æĿ¡
    -0.20
    xaa
    -0.20
    chain
    -0.20
    èµ°åĪ°
    -0.19
    æĿĤ
    -0.19
     Chain
    -0.18
    æī¶
    -0.18
    POSITIVE LOGITS
    é¼ĵ
    0.23
    åıij声
    0.22
    表æ¼Ķ
    0.22
    Bell
    0.19
    ä¹IJåĻ¨
    0.19
    èĨľ
    0.19
     microphone
    0.19
     дÑĥÑħ
    0.19
     guts
    0.19
     оÑĩеÑĢ
    0.19
    Activations Density 0.058%

    No Known Activations