© 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. 12852
    Prev
    Next
    INDEX
    Explanations

    something followed by "wrong" or "like"

    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
    ighted
    -0.20
    enu
    -0.20
    ä¾Ī
    -0.19
     enlist
    -0.18
     Nuggets
    -0.18
    .MM
    -0.18
    ç¿ħ
    -0.18
    омеÑĢ
    -0.17
    stead
    -0.17
    /play
    -0.17
    POSITIVE LOGITS
     Bid
    0.18
     IMPORTANT
    0.17
    tep
    0.17
    ibre
    0.17
    ç´¢åıĸ
    0.17
    _FATAL
    0.17
    车祸
    0.17
    comb
    0.17
    ä¸įåĩº
    0.17
    æĢ»ä¹ĭ
    0.17
    Activations Density 0.022%

    No Known Activations