© 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. 14-TRANSCODER-HP
    7. 39445
    Prev
    Next
    INDEX
    Explanations

    sensitize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ware
    -0.30
    iteDatabase
    -0.29
    stack
    -0.28
    çIJĨ
    -0.28
    å¦ĤæŀľæĤ¨
    -0.27
    å®Ŀ
    -0.27
    éĽĦ
    -0.26
    渡
    -0.26
    stem
    -0.25
     maxX
    -0.25
    POSITIVE LOGITS
    anian
    0.30
    ÑģÑĤо
    0.29
    apia
    0.27
    oes
    0.27
    iola
    0.26
    uil
    0.26
    è§Ħå®ļçļĦ
    0.26
     Giul
    0.25
    pies
    0.25
    OPLE
    0.25
    Activations Density 0.897%

    No Known Activations