© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8107
    Prev
    Next
    INDEX
    Explanations

    detail

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Birthday
    -0.25
    åĨ¼
    -0.25
    atha
    -0.24
    å¸ļ
    -0.24
    orrow
    -0.24
    ultimate
    -0.24
    åIJķ
    -0.23
     Ultimate
    -0.23
    æŀģ
    -0.23
     знаÑĩиÑĤ
    -0.23
    POSITIVE LOGITS
    eni
    0.31
    红线
    0.28
     detail
    0.27
     detailing
    0.27
     details
    0.26
    æŀĦéĢł
    0.26
     fabrics
    0.26
    éĩįå·¥
    0.25
    (details
    0.25
    osal
    0.25
    Activations Density 0.994%

    No Known Activations