© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9332
    Prev
    Next
    INDEX
    Explanations

    numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atsu
    -0.25
    arat
    -0.23
    ”çļĦ
    -0.23
    poss
    -0.23
    unar
    -0.23
    åįĩ
    -0.23
    éļĽ
    -0.22
    å¢ŀéĢŁ
    -0.22
    )”
    -0.22
    çĤ®
    -0.22
    POSITIVE LOGITS
     ext
    0.29
    æĹºçĽĽ
    0.26
    .TryGetValue
    0.26
    æīįå¹²
    0.25
    nee
    0.25
     volumes
    0.25
    IMER
    0.25
    cult
    0.25
    说å®Į
    0.24
     finite
    0.24
    Activations Density 0.024%

    No Known Activations