© 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. 14437
    Prev
    Next
    INDEX
    Explanations

    child abuse and safety

    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
    getParent
    -0.21
    _endian
    -0.20
    ustr
    -0.20
    fore
    -0.19
    äºĮæľŁ
    -0.19
    Plug
    -0.19
    åĭ¢
    -0.18
    Switch
    -0.18
    timing
    -0.18
    ideas
    -0.18
    POSITIVE LOGITS
    å°Ĭ严
    0.20
    -centric
    0.20
     protection
    0.20
    èĥį
    0.20
    ä¸ºçĽ®çļĦ
    0.20
    åĴİ
    0.20
    ä¸ĵ项è¡ĮåĬ¨
    0.20
    -focused
    0.20
    ä¿ĿæĬ¤
    0.19
     Cay
    0.19
    Activations Density 0.016%

    No Known Activations