© 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. 40661
    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
    nor
    -0.30
    交
    -0.28
    ed
    -0.28
    un
    -0.27
     nor
    -0.26
     rid
    -0.26
    /apple
    -0.26
    个åĪ«
    -0.26
    em
    -0.26
    uns
    -0.26
    POSITIVE LOGITS
    lander
    0.29
    tridge
    0.26
    .navigate
    0.25
    èİł
    0.25
    åľ¨æѤä¹ĭåīį
    0.24
     hm
    0.24
    iliated
    0.24
    è¶Ĭ好
    0.24
    ALSE
    0.24
    åºĵéĩĮ
    0.24
    Activations Density 0.100%

    No Known Activations

    This feature has no known activations.