© 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. 39599
    Prev
    Next
    INDEX
    Explanations

    nearness vicinity

    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
    ckpt
    -0.27
    opl
    -0.25
    CENT
    -0.25
    æ³£
    -0.24
     pict
    -0.24
    å®Įæķ´çļĦ
    -0.24
    (PHP
    -0.23
     Comb
    -0.23
    è¿Ļæĺ¯æĪij
    -0.23
    _$_
    -0.23
    POSITIVE LOGITS
    å±Ģ
    0.34
    涯
    0.29
    æĶ¿åºľ
    0.27
     yAxis
    0.27
    rug
    0.26
    åľ°æĸ¹æĶ¿åºľ
    0.26
    sey
    0.25
    igel
    0.25
    çĻ»
    0.25
     government
    0.24
    Activations Density 2.185%

    No Known Activations