© 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. 15893
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
     ÐŁÐ¾Ñĩем
    -0.26
     ÐIJлекÑģан
    -0.21
     ÐĶмиÑĤÑĢ
    -0.20
    uit
    -0.19
    欸
    -0.19
    ëį°
    -0.19
    platz
    -0.18
    /her
    -0.17
     пÑĢекÑĢаÑģн
    -0.17
    eling
    -0.17
    POSITIVE LOGITS
    errupted
    0.20
     uLocal
    0.19
    âĶ§
    0.18
     sourceMapping
    0.17
    媱
    0.17
    rä
    0.17
    æ¶IJ
    0.17
    å§Ī
    0.17
    å©»
    0.17
    ordinator
    0.16
    Activations Density 0.029%

    No Known Activations