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. 146830
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
    xFF
    -0.27
    ,eg
    -0.26
    ÑĦÑĦ
    -0.26
    éĢłä»·
    -0.26
    ä¸Ĭ游
    -0.26
    ecer
    -0.24
    translation
    -0.24
    ãĥ¡ãĥĥ
    -0.24
    tier
    -0.24
    åΤæĸŃ
    -0.24
    POSITIVE LOGITS
    |
    0.26
     Parts
    0.25
    -U
    0.24
    SL
    0.24
     control
    0.24
     parte
    0.24
     fast
    0.23
    ORD
    0.23
     certainly
    0.23
    çīĮ
    0.23
    Activations Density 0.008%

    No Known Activations