© 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. 13220
    Prev
    Next
    INDEX
    Explanations

    crime, incident, accident

    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
    è´²
    -0.24
    èĢ¦
    -0.20
    èĤ¤
    -0.19
    æĦł
    -0.19
    çłĴ
    -0.19
    èĵį
    -0.19
    åħį
    -0.18
    è¾ĥé«ĺ
    -0.18
    è¾ĥå¤ļ
    -0.18
    ода
    -0.18
    POSITIVE LOGITS
     ëĭ¹ìĭľ
    0.26
    å½ĵæŶ
    0.25
    åıijçĶŁåľ¨
    0.23
    å½ĵ天
    0.23
    äºĭ件
    0.23
    å½ĵæĹ¥
    0.22
    äºĭæķħ
    0.22
    åıijçĶŁ
    0.22
    éĤ£å¤©
    0.21
    ç¼ij
    0.21
    Activations Density 0.099%

    No Known Activations