© 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. 25-TRANSCODER-HP
    7. 107067
    Prev
    Next
    INDEX
    Explanations

    say "end in ."

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åı£æ°Ķ
    -0.27
     runaway
    -0.27
    hei
    -0.26
    éo
    -0.25
    å¢ŀé«ĺ
    -0.25
    liest
    -0.25
     Höhe
    -0.25
    ê·Ģ
    -0.25
    usty
    -0.24
     impunity
    -0.24
    POSITIVE LOGITS
    ä¼ı
    0.28
    gal
    0.27
    å¸Ń
    0.27
    ä¸ĢæĹ¥
    0.27
    åľ¨åºĬä¸Ĭ
    0.26
    vette
    0.25
    åľ¨æĪijçļĦ
    0.25
    gra
    0.24
     inc
    0.24
    Breadcrumb
    0.24
    Activations Density 0.945%

    No Known Activations