© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15391
    Prev
    Next
    INDEX
    Explanations

    mental health

    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
    elin
    -0.19
     lá»Ĺi
    -0.18
    é»İæĺİ
    -0.18
    edList
    -0.17
    etting
    -0.17
    ed
    -0.17
    OrCreate
    -0.17
    ever
    -0.16
    ãģ¹ãģį
    -0.16
    yu
    -0.16
    POSITIVE LOGITS
    istic
    0.27
    idades
    0.22
    licity
    0.19
    ized
    0.19
    izations
    0.19
    istically
    0.18
    ogy
    0.17
     пÑĢоÑĩ
    0.17
    /em
    0.17
    mente
    0.17
    Activations Density 0.009%

    No Known Activations