Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 1-TRANSCODER-HP
    4. 240
    Prev
    Next
    INDEX
    Explanations

    locations and tributes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_1.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.1.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /arch
    -0.27
     indefinite
    -0.27
    ä¸įå®ļ
    -0.27
     Stack
    -0.26
    dge
    -0.25
    èĢĮæĪIJ
    -0.25
     krij
    -0.24
    龸
    -0.24
    ularity
    -0.24
    .–
    -0.24
    POSITIVE LOGITS
    owell
    0.30
    妫
    0.27
    å¯Ħ
    0.27
    ä»°
    0.27
    ymoon
    0.25
    yc
    0.24
    .arm
    0.24
    &C
    0.24
    ype
    0.23
    Directories
    0.23
    Activations Density 18.760%

    No Known Activations