© 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. 18-TRANSCODER-HP
    7. 88485
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŀŃ
    -0.29
    éĵº
    -0.28
    好äºĭ
    -0.27
    糧
    -0.26
    æģĥ
    -0.26
    ä¸Ģç«Ļ
    -0.26
    åĬłå·¥
    -0.26
    åģľæĶ¾
    -0.25
    çĶŁäº§çļĦ
    -0.25
     consec
    -0.25
    POSITIVE LOGITS
    .VERSION
    0.25
    raises
    0.25
    éĽĨä½ĵç»ıæµİ
    0.25
    raise
    0.24
    igli
    0.24
    ains
    0.24
    ections
    0.24
    ãĤĴè¶ħ
    0.24
    seealso
    0.23
    èģĶ社
    0.23
    Activations Density 39.859%

    No Known Activations