© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39732
    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
     inc
    -0.29
     pointer
    -0.29
     Pointer
    -0.28
    norm
    -0.27
    ments
    -0.26
    亿ç¾İåħĥ
    -0.25
     needle
    -0.25
    needle
    -0.25
    缸
    -0.25
    Pointer
    -0.25
    POSITIVE LOGITS
    urch
    0.28
    @protocol
    0.28
    _pitch
    0.27
    ymology
    0.25
    Pitch
    0.25
     Carlson
    0.24
     chá»ĭu
    0.24
     Iter
    0.24
    ushman
    0.24
    =YES
    0.23
    Activations Density 0.419%

    No Known Activations

    This feature has no known activations.