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. 146195
    Prev
    Next
    INDEX
    Explanations

    observational

    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
    çļĦçŃĶæ¡Ī
    -0.31
    ick
    -0.30
    icap
    -0.28
    ols
    -0.28
    磫
    -0.28
    çįŃ
    -0.27
     fro
    -0.27
    [$_
    -0.26
    çļĦå®¶åºŃ
    -0.25
    Associ
    -0.25
    POSITIVE LOGITS
    .Pull
    0.29
     oversight
    0.27
    çłĶç©¶éĻ¢
    0.26
    eve
    0.26
    пеÑĢед
    0.26
    ÃŃst
    0.25
    å¸ĮèħĬ
    0.25
    atedRoute
    0.24
    dirname
    0.24
     sider
    0.24
    Activations Density 0.013%

    No Known Activations