© 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. 11625
    Prev
    Next
    INDEX
    Explanations

    hibernate

    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
    活泼
    -0.20
    çĽij管éĥ¨éŨ
    -0.18
    wner
    -0.18
    æľīéĴĪ对æĢ§
    -0.18
    责任å¿ĥ
    -0.18
    sel
    -0.17
    èµį
    -0.17
    ters
    -0.17
    大éĺŁ
    -0.17
    è¾ĩ
    -0.17
    POSITIVE LOGITS
    èĤļåŃIJ
    0.19
     bur
    0.18
    acin
    0.18
    æľŁéĹ´
    0.17
    液
    0.17
    omentum
    0.17
    ographed
    0.17
     Harmony
    0.17
    InstanceState
    0.16
    _like
    0.16
    Activations Density 0.007%

    No Known Activations