© 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. 41432
    Prev
    Next
    INDEX
    Explanations

    Software updates

    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
    çĦ¶
    -0.30
    çĪ¬
    -0.28
    èĬľ
    -0.28
    uters
    -0.28
    cles
    -0.26
    cope
    -0.26
    patch
    -0.26
    ÉĶ
    -0.25
    åij¨åĪĬ
    -0.25
    utar
    -0.25
    POSITIVE LOGITS
    æľŁåĨħ
    0.29
    æŃ»åIJİ
    0.28
    _nullable
    0.26
    çĶŁäº§åĴĮ
    0.26
    ]*)
    0.25
    åŃ£åIJİ
    0.24
    Vs
    0.24
     Niet
    0.24
    åİ¿åŁİ
    0.24
    åħļçļĦé¢Ĩ导
    0.23
    Activations Density 0.089%

    No Known Activations