© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161661
    Prev
    Next
    INDEX
    Explanations

    Code/math/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ¬å¤´
    -0.32
     showers
    -0.27
    ä½İ头
    -0.26
     anale
    -0.25
    anio
    -0.25
    èľľèľĤ
    -0.25
     shower
    -0.24
    motion
    -0.24
    upa
    -0.24
    Devices
    -0.24
    POSITIVE LOGITS
    hal
    0.28
    ä¿¡åı·
    0.26
    (pow
    0.25
     Gaul
    0.25
     skewed
    0.24
     hon
    0.24
    odial
    0.24
    DisplayStyle
    0.24
    æĬĬæı¡
    0.24
    ä½
    0.24
    Activations Density 0.002%

    No Known Activations