© 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. 39737
    Prev
    Next
    INDEX
    Explanations

    computer code & technical content

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çģ«æĺŁ
    -0.29
    mode
    -0.27
    inho
    -0.27
    å°ıå§IJ
    -0.26
    磨
    -0.26
     brains
    -0.26
    åĸĿäºĨ
    -0.25
    å®ŀä½ĵåºĹ
    -0.24
    quito
    -0.24
    ottle
    -0.24
    POSITIVE LOGITS
    untary
    0.27
    isci
    0.27
    _strerror
    0.27
    裸
    0.26
     Permanent
    0.25
    éľľ
    0.25
     automat
    0.25
    éĤ»
    0.25
    è§Ħå¾ĭ
    0.24
     Profession
    0.24
    Activations Density 0.059%

    No Known Activations