© 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. 40389
    Prev
    Next
    INDEX
    Explanations

    Code and unusual text

    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
    predicate
    -0.27
    astics
    -0.27
    ä¸Ģ身
    -0.26
    _predicate
    -0.26
    ç¾İèªī
    -0.25
    宪
    -0.25
    ôme
    -0.25
     Ancient
    -0.24
    epar
    -0.24
    umer
    -0.24
    POSITIVE LOGITS
     UsersController
    0.28
    zeug
    0.27
    æľīä»Ģä¹Ī
    0.26
    æľīä½ķ
    0.25
    ulk
    0.25
    沿
    0.24
    LayoutInflater
    0.24
    istle
    0.24
    íĺ¸
    0.24
     Brook
    0.23
    Activations Density 1.814%

    No Known Activations