© 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. 12320
    Prev
    Next
    INDEX
    Explanations

    cloning and reproduction

    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
    æ¡£
    -0.21
    çĹ¹
    -0.19
    erd
    -0.19
    笼
    -0.19
    ~/
    -0.18
    sembly
    -0.18
    èĥĮæĻ¯
    -0.18
    æ±ĩèģļ
    -0.18
    .va
    -0.18
    æ¸IJ
    -0.18
    POSITIVE LOGITS
    ç¹ģæ®ĸ
    0.35
     cloning
    0.26
     reproduction
    0.25
    (clone
    0.25
    _seed
    0.23
     clones
    0.23
    æĤ¬å´ĸ
    0.22
    Clone
    0.22
    _hosts
    0.22
    _boot
    0.21
    Activations Density 0.097%

    No Known Activations