© 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. 14466
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
     ÐIJлекÑģан
    -0.21
    IDER
    -0.20
    MAS
    -0.20
    ivor
    -0.19
    ISTER
    -0.19
    anst
    -0.18
    æĹłæ¯Ķ
    -0.18
     HOWEVER
    -0.17
    ĥģ
    -0.17
    使çĶ¨
    -0.17
    POSITIVE LOGITS
     utmost
    0.20
    dar
    0.19
     damn
    0.18
    éĻIJè´Ń
    0.18
    ç¬
    0.17
     darn
    0.17
    å¤Ł
    0.17
    ç¦ĺ
    0.17
    mediately
    0.17
    wij
    0.17
    Activations Density 0.082%

    No Known Activations