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. 46443
    Prev
    Next
    INDEX
    Explanations

    Cardinal

    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
    ]byte
    -0.25
     matrix
    -0.24
    ibase
    -0.24
    çݰ代çµģ
    -0.24
    pring
    -0.24
    åĵ¥ä¼¦
    -0.24
     "__
    -0.24
    handling
    -0.23
    ugg
    -0.23
    _macros
    -0.23
    POSITIVE LOGITS
    社ä¼ļèµĦæľ¬
    0.28
    udu
    0.27
    .getFile
    0.26
    звÑĥÑĩ
    0.26
    iet
    0.25
    æľ¨è̳
    0.25
    æ¯Ļ
    0.25
    irsch
    0.25
    Susan
    0.25
    ayne
    0.24
    Activations Density 0.071%

    No Known Activations