© 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. 12537
    Prev
    Next
    INDEX
    Explanations

    remaining or left out

    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
     Spin
    -0.22
    çĪ±å¥½
    -0.19
    Spin
    -0.19
    agna
    -0.18
    iat
    -0.18
    ä¸Ģ对
    -0.17
    ãģ¤ãģĦ
    -0.17
     BH
    -0.17
    ró
    -0.17
    allis
    -0.17
    POSITIVE LOGITS
    remaining
    0.31
    Remaining
    0.28
     remaining
    0.27
    åī©ä¸ĭçļĦ
    0.25
    åī©ä½Ļ
    0.25
    继ç»Ń
    0.24
    éģĹçķĻ
    0.23
    .remaining
    0.23
     Remaining
    0.23
    ä»įæľī
    0.22
    Activations Density 0.072%

    No Known Activations