© 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. 41772
    Prev
    Next
    INDEX
    Explanations

    still

    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
    Negative Logits
    -minus
    -0.28
    ÅĤÄħ
    -0.25
    -Length
    -0.24
    .Ge
    -0.24
    appa
    -0.24
    åħ¬å¸ĥ
    -0.24
     unveil
    -0.24
    UCT
    -0.24
    roscope
    -0.23
    -Christian
    -0.23
    POSITIVE LOGITS
    cow
    0.27
     lay
    0.27
    跨度
    0.24
    é£İéĻ©
    0.24
    çĹ´
    0.24
     promotion
    0.24
     kes
    0.24
    äºļ太
    0.24
     unsupported
    0.24
     Lay
    0.24
    Activations Density 0.084%

    No Known Activations