© 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. 12377
    Prev
    Next
    INDEX
    Explanations

    report abuse, complaints, flagging issues

    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
    éĢŀ
    -0.20
    èµ°åħ¥
    -0.20
    intro
    -0.20
    รà¸Ńà¸ĩ
    -0.20
    urch
    -0.20
    ẹ
    -0.20
    çĹ´
    -0.19
    ä¸ĩåı°
    -0.19
    .jp
    -0.18
    赶ä¸Ĭ
    -0.18
    POSITIVE LOGITS
    举æĬ¥
    0.50
    æĬķè¯ī
    0.34
    线索
    0.33
     complaints
    0.32
     Complaint
    0.31
    举æĬ¥çĶµè¯Ŀ
    0.27
     complaint
    0.26
    æĬ¥åijĬ
    0.26
    è¯īæ±Ĥ
    0.26
    请æ±Ĥ
    0.25
    Activations Density 0.164%

    No Known Activations