© 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. 40083
    Prev
    Next
    INDEX
    Explanations

    operative

    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
    ä¹ĭä½Ļ
    -0.26
    ollar
    -0.26
     доволÑĮ
    -0.25
    dez
    -0.25
    afia
    -0.25
    icone
    -0.25
    èı½
    -0.25
    沸
    -0.24
    ï¼Ł”
    -0.24
    /games
    -0.24
    POSITIVE LOGITS
    ä»ĸ们çļĦ
    0.27
    箧
    0.27
    _repeat
    0.26
    个èĤ¡
    0.26
     new
    0.26
    asp
    0.26
     portal
    0.25
     site
    0.25
    èµ°è¿Ľ
    0.25
    ä¸Ĭç½ij
    0.24
    Activations Density 0.232%

    No Known Activations