© 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. 14722
    Prev
    Next
    INDEX
    Explanations

    FILE folder Q Ass Football

    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
    .Constants
    -0.22
    intent
    -0.22
    kt
    -0.19
    ello
    -0.19
     Come
    -0.18
    med
    -0.18
    available
    -0.18
    Assistant
    -0.18
     Wars
    -0.18
    .intent
    -0.18
    POSITIVE LOGITS
     ÑĥнивеÑĢÑģиÑĤеÑĤ
    0.25
    票
    0.21
    жа
    0.20
    æ»´
    0.20
     arsch
    0.20
    orsk
    0.19
    åĮĹ京大åѦ
    0.19
    .Infrastructure
    0.19
     tickets
    0.19
    ä¸Ģæĸ¹
    0.19
    Activations Density 0.069%

    No Known Activations