© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41236
    Prev
    Next
    INDEX
    Explanations

    Justification and Justin

    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
     Licence
    -0.31
    ä¸Ńåħ³
    -0.31
    许åı¯
    -0.28
    -release
    -0.27
    å¼ķ
    -0.27
    èĭ¥æĤ¨
    -0.26
    zell
    -0.25
    æ³Ľ
    -0.25
    åĵĨ
    -0.24
    bidden
    -0.24
    POSITIVE LOGITS
    Rem
    0.29
    ea
    0.28
    ensis
    0.27
     Rim
    0.27
     Rem
    0.26
    好好
    0.26
    é¤ĺ
    0.25
    gars
    0.25
     Verse
    0.25
     consistent
    0.25
    Activations Density 0.101%

    No Known Activations