© 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. 11094
    Prev
    Next
    INDEX
    Explanations

    Kolkata, India

    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
    åı¯çĪ±çļĦ
    -0.21
    maid
    -0.21
    gent
    -0.18
    istrator
    -0.18
    åŃ°
    -0.17
    æĪijå¦Ī
    -0.17
    åŃIJéĩĮ
    -0.17
    holm
    -0.17
    亲çĪ±
    -0.17
    失踪
    -0.17
    POSITIVE LOGITS
    jin
    0.18
    dont
    0.18
    çĪº
    0.18
    è¯Ħ
    0.17
    ffen
    0.16
     eff
    0.16
    aul
    0.16
     chooser
    0.16
    _ulong
    0.16
    gMaps
    0.16
    Activations Density 0.002%

    No Known Activations