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. 146310
    Prev
    Next
    INDEX
    Explanations

    internet/forum content

    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
     drains
    -0.29
     juices
    -0.27
    dy
    -0.26
     unic
    -0.26
    omi
    -0.26
     excav
    -0.26
    è¡¡
    -0.26
    ä¸Ģç»ı
    -0.25
    borne
    -0.25
    ilon
    -0.25
    POSITIVE LOGITS
    uParam
    0.27
    &q
    0.27
    åºĦ
    0.25
    产
    0.24
    xsd
    0.24
    sse
    0.24
     Manuals
    0.24
    @Table
    0.24
    atables
    0.24
    USAGE
    0.23
    Activations Density 0.014%

    No Known Activations