© 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. 40357
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     downstream
    -0.26
     licens
    -0.25
    缺
    -0.25
    Terminal
    -0.25
    å·¡åĽŀ
    -0.25
    çİĩ为
    -0.25
     Layer
    -0.24
     terminal
    -0.24
    åħ±æľī
    -0.24
    Layer
    -0.23
    POSITIVE LOGITS
    apo
    0.33
    ored
    0.31
    çIJ°
    0.25
    ammed
    0.24
    usta
    0.24
     plead
    0.24
    edin
    0.24
     pronounced
    0.24
    abi
    0.24
    ç»ıéªĮ丰å¯Į
    0.23
    Activations Density 3.251%

    No Known Activations

    This feature has no known activations.