© 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. 40556
    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
    unders
    -0.29
    -↵
    -0.28
    æĪİ
    -0.27
    åĤį
    -0.26
    ä¸įåıĬ
    -0.26
    æķĪåĬĽ
    -0.26
    .ravel
    -0.25
     None
    -0.25
     "#"
    -0.25
     queries
    -0.25
    POSITIVE LOGITS
    æ´»ä¸ĭåİ»
    0.28
     neger
    0.28
    blk
    0.26
    _cb
    0.25
     sob
    0.25
    .quant
    0.25
    imet
    0.25
    NSE
    0.25
    ObjectType
    0.24
    EZ
    0.24
    Activations Density 0.060%

    No Known Activations

    This feature has no known activations.