© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129382
    Prev
    Next
    INDEX
    Explanations

    General text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessException
    -0.28
    泸
    -0.27
    çĤ¯
    -0.26
     Trouble
    -0.26
    ä¸ªé¡¹çĽ®
    -0.25
     unloaded
    -0.24
    å¼Ģåĩº
    -0.24
    ogi
    -0.24
     :'
    -0.24
    :S
    -0.24
    POSITIVE LOGITS
    æĺ¯ä¸ºäºĨ
    0.47
    çļĦ缮çļĦ
    0.45
    å°±æĺ¯ä¸ºäºĨ
    0.42
     aimed
    0.41
     goal
    0.41
     priorit
    0.41
    缮çļĦ
    0.40
     prioritize
    0.39
    为äºĨ
    0.38
     aiming
    0.38
    Activations Density 55.857%

    No Known Activations