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. 23-TRANSCODER-HP
    4. 7447
    Prev
    Next
    INDEX
    Explanations

    Code and technical jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APT
    -0.28
    onga
    -0.28
    fried
    -0.27
    fad
    -0.26
    strain
    -0.26
     Freed
    -0.25
    两æĿ¡
    -0.25
    ÑĤиÑĢ
    -0.25
    模仿
    -0.25
     drive
    -0.25
    POSITIVE LOGITS
    ists
    0.28
     önce
    0.25
     hus
    0.25
    igans
    0.25
    igan
    0.25
    istically
    0.25
    hof
    0.25
    æ°§
    0.24
    clusive
    0.24
    lah
    0.24
    Activations Density 0.010%

    No Known Activations