© 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. 12529
    Prev
    Next
    INDEX
    Explanations

    agree with

    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
     themselves
    -0.26
    iskey
    -0.22
    èŀįèµĦ
    -0.19
    usi
    -0.19
    ':['
    -0.19
    hasil
    -0.19
    ":["
    -0.18
    ORIZ
    -0.18
    iran
    -0.18
     varying
    -0.18
    POSITIVE LOGITS
    [color
    0.21
    ä¸Ŀä¸Ŀ
    0.21
     sentiments
    0.21
    ovah
    0.20
    å¨ĺ家
    0.20
    俪
    0.20
    оÑĩка
    0.19
     Æ¡n
    0.19
    acon
    0.19
    楼ä¸Ĭ
    0.18
    Activations Density 0.013%

    No Known Activations