© 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. 141463
    Prev
    Next
    INDEX
    Explanations

    Varied narrative/news context

    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
    æĪĸå¤ļ
    -0.30
    ione
    -0.28
    質
    -0.25
    insi
    -0.24
    ieux
    -0.24
    á»ıi
    -0.24
    马åħĭæĢĿ
    -0.24
    è°·çĪ±åĩĮ
    -0.24
     tul
    -0.24
    èĭ¥å¹²
    -0.24
    POSITIVE LOGITS
    æŀģ端
    0.29
    俱
    0.28
     extreme
    0.27
    łģ
    0.26
     dict
    0.26
    ä¸ĭçļĦ
    0.25
    ifecycle
    0.25
     beneath
    0.25
    )init
    0.25
     undergoing
    0.24
    Activations Density 12.055%

    No Known Activations