© 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. 12657
    Prev
    Next
    INDEX
    Explanations

    autism spectrum

    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
    éĺŁéķ¿
    -0.19
    主任
    -0.18
    çĽĹ
    -0.17
    èµ°ç§ģ
    -0.17
    UserController
    -0.16
    æĭ¢
    -0.15
    缯
    -0.15
    viron
    -0.15
    userName
    -0.15
    лаÑĤ
    -0.15
    POSITIVE LOGITS
    çĹĩ
    0.22
    Ĵ
    0.20
    ened
    0.20
    -like
    0.18
    èĥĮæĻ¯ä¸ĭ
    0.17
    like
    0.17
     spectrum
    0.17
    apes
    0.17
    izable
    0.16
    åıŁ
    0.16
    Activations Density 0.005%

    No Known Activations