© 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. 16464
    Prev
    Next
    INDEX
    Explanations

    of use or the

    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
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.21
    erp
    -0.20
    离
    -0.20
    åij·
    -0.18
     uniform
    -0.17
     mane
    -0.17
    èĵĿ
    -0.17
    丽
    -0.17
    -col
    -0.17
    virt
    -0.17
    POSITIVE LOGITS
    éĵµ
    0.23
    éĵį
    0.23
    æ³Ħ
    0.20
     münchen
    0.20
    ffset
    0.19
    交åıĭ
    0.19
    éªĮæĶ¶
    0.18
    alsex
    0.18
    äºļ马
    0.18
    æĤ¬
    0.18
    Activations Density 0.040%

    No Known Activations