© 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. 13088
    Prev
    Next
    INDEX
    Explanations

    .com Paper

    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
    esk
    -0.20
     æ¸
    -0.19
    æ¥Ķ
    -0.19
    æľĢç¾İ
    -0.19
    å¡ĺ
    -0.19
    enis
    -0.18
    éĢŁåº¦å¿«
    -0.18
    Ùĥا
    -0.18
    erald
    -0.18
    å°Ŀ
    -0.18
    POSITIVE LOGITS
    Ñģад
    0.19
    å¼ķãģį
    0.19
    amins
    0.19
    é¦ı
    0.18
    [channel
    0.18
    æ¼Ķç»İ
    0.17
    .Pin
    0.17
    _mC
    0.17
    <!--[
    0.17
    KNOWN
    0.17
    Activations Density 0.005%

    No Known Activations