© 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. 39731
    Prev
    Next
    INDEX
    Explanations

    Describing buildings and structures

    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
     tiá»ģm
    -0.26
    æĻ¤
    -0.26
    igram
    -0.26
    åĬŁå¾·
    -0.26
    sky
    -0.25
    oms
    -0.25
     unfold
    -0.25
    èĵĿåĽ¾
    -0.25
    matic
    -0.25
     pil
    -0.24
    POSITIVE LOGITS
    åĿļ强
    0.29
    æĬĬ她
    0.26
    .TabControl
    0.26
    uchos
    0.26
    ä¸ŃåĽ½å¤§éĻĨ
    0.25
    .deg
    0.25
     lcm
    0.25
    èĩªçĶ±
    0.25
    esson
    0.24
    èħĶ
    0.24
    Activations Density 0.104%

    No Known Activations