© 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. 40066
    Prev
    Next
    INDEX
    Explanations

    to will

    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
    ussen
    -0.27
    ousing
    -0.26
    å¼Ģ端
    -0.26
    ativity
    -0.26
    ppe
    -0.26
    纹
    -0.26
    yne
    -0.25
    awan
    -0.25
     peer
    -0.23
    uppe
    -0.23
    POSITIVE LOGITS
    myModal
    0.26
    åľ¨åŃ¦æł¡
    0.25
    ogn
    0.25
    icz
    0.24
    åĮºæĶ¿åºľ
    0.24
    绿èī²éĢļéģĵ
    0.24
    éĶĻè¿ĩäºĨ
    0.24
    among
    0.23
    \Doctrine
    0.23
    aph
    0.23
    Activations Density 0.421%

    No Known Activations