© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12645
    Prev
    Next
    INDEX
    Explanations

    title or script headers

    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
    æĮŀ
    -0.21
    åħ»çĶŁ
    -0.19
    лом
    -0.19
    è¿ĺåİŁ
    -0.19
    icious
    -0.19
    豪
    -0.18
    _password
    -0.18
    女åıĭ
    -0.18
    .reference
    -0.18
    owler
    -0.18
    POSITIVE LOGITS
     iframe
    0.20
    rieve
    0.19
    åľ°æĸ¹
    0.18
    éģĨ
    0.18
    ARN
    0.18
    æĪijçľģ
    0.18
    /List
    0.17
     Places
    0.17
    è¿ĻçĤ¹
    0.17
     Courses
    0.17
    Activations Density 0.004%

    No Known Activations