© 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. 13010
    Prev
    Next
    INDEX
    Explanations

    sexual abuse and exploitation

    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
    IRM
    -0.22
    å°ıå§IJ
    -0.21
    è§īå¾Ĺèĩªå·±
    -0.21
    娥
    -0.20
     меÑĤалл
    -0.20
     exh
    -0.20
    çŁ¿çī©è´¨
    -0.19
    çĽ¸ä¿¡
    -0.19
    iani
    -0.18
    åģ¶çĦ¶
    -0.18
    POSITIVE LOGITS
    åĦ¿ç«¥
    0.32
    åħĴç«¥
    0.28
     children
    0.24
    åĤħ
    0.23
    oulos
    0.21
    rapper
    0.20
    .sav
    0.20
    è¡Į为
    0.20
    棣
    0.20
     Children
    0.19
    Activations Density 0.015%

    No Known Activations