© 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. 12404
    Prev
    Next
    INDEX
    Explanations

    mail surveys and questionnaires

    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
    _HDR
    -0.21
    éĺ¡
    -0.20
    次ä¼ļè®®
    -0.20
    èħ¥
    -0.18
     Tac
    -0.18
    æĪ½
    -0.18
    åľ³
    -0.18
    bz
    -0.17
    è¿ĻåĦ¿
    -0.17
    å·²å®ĮæĪIJ
    -0.17
    POSITIVE LOGITS
    éĤ®å¯Ħ
    0.23
    postal
    0.23
    letters
    0.23
    Letters
    0.23
     letters
    0.21
    éĤ®
    0.21
    éĤ¸
    0.20
    å®ŀä½ĵ
    0.20
    _letters
    0.20
    PACE
    0.20
    Activations Density 0.020%

    No Known Activations