© 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. 11675
    Prev
    Next
    INDEX
    Explanations

    spinning, rotating, storage, media, frequency, server

    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
    ilot
    -0.25
    èįī
    -0.20
    èĬĭ
    -0.20
    dee
    -0.19
    ILED
    -0.19
    aring
    -0.19
    dé
    -0.18
    Dé
    -0.18
    æ»´æ»´
    -0.18
    .uuid
    -0.18
    POSITIVE LOGITS
    éķ¿çĽ¸
    0.23
    éĶ»éĢł
    0.21
    é«ĺå±±
    0.20
     меÑĤÑĢо
    0.19
    çİij
    0.19
    é£İæīĩ
    0.19
    ç¼Ľ
    0.19
    磾
    0.19
    æĽ´é«ĺçļĦ
    0.19
    ой
    0.19
    Activations Density 0.005%

    No Known Activations