© 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. 14416
    Prev
    Next
    INDEX
    Explanations

    inner girl/woman relationships

    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
    iben
    -0.23
    鸳
    -0.21
    é£İè²Į
    -0.21
    egend
    -0.21
    ayne
    -0.20
     Miracle
    -0.20
    ç¥ļ
    -0.20
    illian
    -0.20
     Bowen
    -0.19
    豪
    -0.19
    POSITIVE LOGITS
     control
    0.24
     вÑģÑıк
    0.21
    æīĵæŀ¶
    0.21
    (Control
    0.21
    _Control
    0.21
     ÙĬÙĪس
    0.21
     вÑģÑı
    0.20
    плод
    0.19
     Control
    0.19
     Modi
    0.19
    Activations Density 0.060%

    No Known Activations