© 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. 41415
    Prev
    Next
    INDEX
    Explanations

    work

    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
    Not in Any Lists

    No Comments

    Negative Logits
    unker
    -0.25
     footnote
    -0.25
    åĭĻ
    -0.24
    ç¯ĩ
    -0.24
    ermint
    -0.24
    说è¿ĩ
    -0.24
    enade
    -0.24
    æ§ģ
    -0.24
    ulum
    -0.24
    æ¦ľé¦ĸ
    -0.24
    POSITIVE LOGITS
    æĭŁ
    0.28
    çĶ¨äºº
    0.26
    /sources
    0.26
    è¿
    0.25
     bevor
    0.25
     Cay
    0.25
    èĢģçĪ·
    0.24
    """.
    0.24
    ême
    0.24
    亲åĪĩ
    0.24
    Activations Density 0.167%

    No Known Activations