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. 11-TRANSCODER-HP
    4. 47258
    Prev
    Next
    INDEX
    Explanations

    dates and technical specs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     liv
    -0.26
    è·»
    -0.24
    _cats
    -0.24
    gradient
    -0.24
     searchData
    -0.24
     decor
    -0.24
    YLON
    -0.24
    .SubItems
    -0.23
    (ld
    -0.23
    åijĬçŁ¥
    -0.23
    POSITIVE LOGITS
    iscopal
    0.27
    wal
    0.26
    ust
    0.26
    phabet
    0.26
    _CONFIGURATION
    0.25
    åģļäºĭ
    0.25
    UST
    0.25
    æĪŁ
    0.25
    bay
    0.25
    configs
    0.24
    Activations Density 0.022%

    No Known Activations