© 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. 14328
    Prev
    Next
    INDEX
    Explanations

    facts about

    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
    ROLS
    -0.19
    ihat
    -0.19
    cket
    -0.18
    inati
    -0.18
    _DMA
    -0.18
    aho
    -0.18
    使å¾Ĺ
    -0.18
     rig
    -0.18
    HeaderCode
    -0.18
    ãģ£ãģ±
    -0.18
    POSITIVE LOGITS
    å®ŀäºĭæ±Ĥæĺ¯
    0.25
    羣è¯ļ
    0.21
    è´ŁéĿ¢
    0.21
    æľ½
    0.20
    æ¶Īæŀģ
    0.19
     каÑĤегоÑĢ
    0.19
    è¯ļå®ŀ
    0.19
    ä¸Ģ件äºĭæĥħ
    0.19
    åĿļåĨ³
    0.19
    mel
    0.18
    Activations Density 0.004%

    No Known Activations