© 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. 13099
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by body part

    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
    à¸Ĥà¸Ļา
    -0.23
     пÑĢиÑıÑĤн
    -0.21
    ouro
    -0.21
     recent
    -0.20
    åĴ³
    -0.19
     sanity
    -0.19
     review
    -0.18
    ÑĩÑĢежден
    -0.18
     program
    -0.18
     consolidated
    -0.18
    POSITIVE LOGITS
    æīĵæŀ¶
    0.24
    digits
    0.23
    讲æķħäºĭ
    0.23
    ç½ijåıĭè¯Ħ论
    0.21
    dispatcher
    0.21
    éĴ±å¸ģ
    0.20
    ä¸ī大èģĮä¸ļ
    0.20
    _ALARM
    0.20
    cles
    0.19
    广æĴŃçĶµè§Ĩ
    0.19
    Activations Density 0.041%

    No Known Activations