© 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
    2. Qwen3-4B
    3. 20-TRANSCODER-HP
    4. 130360
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    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
    esi
    -0.27
    为客æĪ·
    -0.27
     nose
    -0.26
    夹
    -0.25
     negatives
    -0.25
    éĺĸ
    -0.24
    俯
    -0.24
    åĵĦ
    -0.24
    èĻ¹æ¡¥
    -0.23
    uit
    -0.23
    POSITIVE LOGITS
    å½ĵä¹ĭ
    0.27
    chia
    0.25
    izophren
    0.25
    å½Ŀ
    0.25
    levision
    0.25
    票
    0.24
    çķ
    0.24
     Dak
    0.24
     Vaccine
    0.24
    currentColor
    0.24
    Activations Density 15.927%

    No Known Activations