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. 7-TRANSCODER-HP
    4. 72111
    Prev
    Next
    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .—
    -0.29
    pez
    -0.28
    hores
    -0.27
    vet
    -0.26
    ertype
    -0.25
    ())),↵
    -0.24
    .sem
    -0.24
    highest
    -0.23
    ç»ĻæĤ¨
    -0.23
    çľĹ
    -0.23
    POSITIVE LOGITS
    atable
    0.31
    plate
    0.25
     Plate
    0.25
    åĨįéĢł
    0.25
     ÑĢоман
    0.25
    ất
    0.24
    ç§ŁæĪ¿
    0.24
    !
    0.24
    åŁºç¡Ģ
    0.24
     mb
    0.23
    Activations Density 0.005%

    No Known Activations