© 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. 16691
    Prev
    Next
    INDEX
    Explanations

    o' names

    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
    ÑĤÑģÑı
    -0.19
    亲
    -0.19
     pre
    -0.18
    éĻIJãĤĬ
    -0.18
    ä½łèĩªå·±
    -0.18
    ä»İåīį
    -0.18
     form
    -0.18
    es
    -0.17
     support
    -0.17
     pac
    -0.17
    POSITIVE LOGITS
     backpage
    0.21
    azı
    0.20
    Óĵ
    0.19
     bÃło
    0.18
    _AdjustorThunk
    0.18
     norge
    0.18
    åħ¸
    0.17
     taxp
    0.17
    aters
    0.17
    彩票
    0.17
    Activations Density 0.020%

    No Known Activations