© 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. 15010
    Prev
    Next
    INDEX
    Explanations

    major, big, substantial

    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
    Çľ
    -0.24
    ttl
    -0.20
    olu
    -0.19
    个å°ı
    -0.19
     наг
    -0.18
    íĥľ
    -0.18
    ensa
    -0.18
    ä¸ĸçķĮ第ä¸Ģ
    -0.17
     CASCADE
    -0.17
    ipers
    -0.17
    POSITIVE LOGITS
     enough
    0.23
    -sized
    0.23
     sized
    0.22
    大è§Ħ模
    0.21
     Sized
    0.21
    -scale
    0.20
    Enough
    0.20
    /high
    0.20
    ä¸Ģéĺµ
    0.20
     Enough
    0.19
    Activations Density 0.165%

    No Known Activations