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. 7605
    Prev
    Next
    INDEX
    Explanations

    if

    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
    ney
    -0.28
     specifying
    -0.27
    åĽº
    -0.26
    æĽ¿
    -0.26
    åıī
    -0.25
     politic
    -0.25
    宿
    -0.25
    leasing
    -0.25
    ifi
    -0.24
    è·ŁçĿĢ
    -0.24
    POSITIVE LOGITS
     !
    0.28
     (!((
    0.27
     "".
    0.27
     !(
    0.27
    argc
    0.27
     prof
    0.27
    =bool
    0.26
    isNull
    0.26
     profess
    0.26
    .IsEmpty
    0.25
    Activations Density 0.166%

    No Known Activations