© 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. 39703
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
    æĮģä¹ħ
    -0.27
    ä¸Ŀ
    -0.26
    åŃ°
    -0.25
     pulumi
    -0.24
    ç¥Ł
    -0.24
     exper
    -0.24
    $class
    -0.24
    æŁı
    -0.24
    pisa
    -0.24
    iline
    -0.23
    POSITIVE LOGITS
    åħ±
    0.27
     assass
    0.26
    å½ķçĶ¨
    0.25
    StateException
    0.25
    rze
    0.24
    æİĴéĻ¤
    0.24
    å°¼äºļ
    0.24
     numbering
    0.24
     Vulner
    0.23
     nutshell
    0.23
    Activations Density 0.296%

    No Known Activations