© 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. 14640
    Prev
    Next
    INDEX
    Explanations

    anemia

    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
    ç¤ģ
    -0.22
    æĥ©æĪĴ
    -0.22
    allee
    -0.21
    ä¹Ŀåįģ
    -0.21
    çĸĸ
    -0.20
    gMaps
    -0.20
     knull
    -0.19
    _EVT
    -0.19
     erotisk
    -0.18
    cott
    -0.18
    POSITIVE LOGITS
    è´«è¡Ģ
    0.33
    è¡Ģ
    0.29
     blood
    0.27
    çĮ®è¡Ģ
    0.24
    è¡Ģ液
    0.24
    éĢłè¡Ģ
    0.24
     circulating
    0.23
     кÑĢови
    0.23
    ä¸Ńéĵģ
    0.23
    emia
    0.22
    Activations Density 0.098%

    No Known Activations