© 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. 11228
    Prev
    Next
    INDEX
    Explanations

    that followed by conjunctions or clauses

    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
    è¿ĽæĿ¥
    -0.19
    è¿ĩæĪ·
    -0.19
    æĺİçŁ¥
    -0.19
    说æĺ¯
    -0.18
    å®ı大
    -0.18
    æĪijå¿ĥéĩĮ
    -0.18
    å¤Ł
    -0.18
    为äºĨ让
    -0.17
     Asked
    -0.17
    Assignable
    -0.17
    POSITIVE LOGITS
     consequently
    0.20
    _modifier
    0.19
    жен
    0.18
     اÙĦØ£Ùħر
    0.18
    avor
    0.18
    ERO
    0.18
     dabei
    0.18
     therefore
    0.18
    _taken
    0.17
    éro
    0.17
    Activations Density 0.032%

    No Known Activations