© 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. 14018
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by punctuation or specific words

    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
    认æ¸ħ
    -0.18
    å¸IJ篷
    -0.18
    æķ£çĥŃ
    -0.17
    æĸ¹åľĨ
    -0.17
    éĢļé£İ
    -0.17
    éĴµ
    -0.17
    ä½ľä¸ºä¸ĢåIJį
    -0.16
    éľĵ
    -0.16
    ÑģÑĤи
    -0.16
    æij¸
    -0.16
    POSITIVE LOGITS
    ฯ
    0.21
    IDD
    0.20
    unk
    0.19
    alc
    0.18
    ulla
    0.18
    semb
    0.18
    inally
    0.18
     Jerome
    0.18
    aml
    0.17
    redd
    0.17
    Activations Density 0.262%

    No Known Activations