© 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. 40778
    Prev
    Next
    INDEX
    Explanations

    Code and formal 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
    ADED
    -0.28
     Gör
    -0.26
    afs
    -0.26
    缩水
    -0.26
     analogue
    -0.26
    (undefined
    -0.25
     brethren
    -0.25
    ç«¿
    -0.24
    anca
    -0.24
    Overview
    -0.24
    POSITIVE LOGITS
    lug
    0.26
    è½®åĽŀ
    0.26
    olynomial
    0.24
    Mul
    0.24
    est
    0.24
    NewItem
    0.23
     CActive
    0.23
    缮
    0.23
    oll
    0.23
    æļĤæŶ
    0.23
    Activations Density 0.286%

    No Known Activations