© 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. 107169
    Prev
    Next
    INDEX
    Explanations

    Code and file operations

    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
    æ¶Ĥ
    -0.31
    æ¶ĤæĬ¹
    -0.29
    eka
    -0.26
    åĴĮå¹³
    -0.25
     rekl
    -0.25
    ç©¿æĪ´
    -0.25
    aways
    -0.25
    ifestyle
    -0.24
    ilk
    -0.24
    黾
    -0.24
    POSITIVE LOGITS
    æĺİ代
    0.27
    (Const
    0.26
    |#
    0.26
    anium
    0.26
     closed
    0.25
    æ°ijå¿ĥ
    0.25
    å²ģçļĦ
    0.25
    unless
    0.25
    _AUT
    0.24
    /open
    0.24
    Activations Density 1.038%

    No Known Activations