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. 53418
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    issing
    -0.27
    (Cl
    -0.26
    AUTO
    -0.26
    vor
    -0.26
    ä¿Ĥ
    -0.25
    俱ä¹IJéĥ¨
    -0.25
     boca
    -0.25
    isle
    -0.25
     topology
    -0.24
    .baidu
    -0.24
    POSITIVE LOGITS
    泪
    0.28
     zakÅĤad
    0.27
     misc
    0.27
    .protocol
    0.26
    heck
    0.26
    atego
    0.25
    æļĤ
    0.25
    Enumerator
    0.25
     tabs
    0.24
    ointments
    0.24
    Activations Density 0.012%

    No Known Activations