© 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. 12-TRANSCODER-HP
    7. 22286
    Prev
    Next
    INDEX
    Explanations

    -pr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    交代
    -0.27
     statically
    -0.27
    Formats
    -0.27
    说æĺİ书
    -0.25
     manuals
    -0.25
    éĿľ
    -0.25
    éĿĻ
    -0.24
    åįĬæľĪ
    -0.24
    _inactive
    -0.24
     Formats
    -0.24
    POSITIVE LOGITS
    c
    0.28
    ?
    0.24
    ä¸Ń
    0.24
    åħĥ
    0.24
     intervention
    0.24
    çıŀ
    0.24
    centration
    0.23
    åĿļå®ļä¸į
    0.23
    å¹²é¢Ħ
    0.23
    aunch
    0.23
    Activations Density 0.001%

    No Known Activations