© 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. 4-TRANSCODER-HP
    7. 367
    Prev
    Next
    INDEX
    Explanations

    office software and databases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Capacity
    -0.27
     capacity
    -0.27
     capacities
    -0.26
    åijµ
    -0.26
    Capacity
    -0.26
    éĻIJãĤĬ
    -0.25
    容
    -0.25
    capacity
    -0.23
     conse
    -0.23
    gó
    -0.23
    POSITIVE LOGITS
    绣ä¸Ģ
    0.26
    iche
    0.24
    èĦĨ
    0.24
    throat
    0.24
     michael
    0.24
    骥
    0.23
    eson
    0.23
    _AX
    0.23
    建æĪIJåIJİ
    0.23
    tasks
    0.23
    Activations Density 0.083%

    No Known Activations