© 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. 25-TRANSCODER-HP
    7. 109510
    Prev
    Next
    INDEX
    Explanations

    Code and IP addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çľĭä»ĸ
    -0.28
    缸éĢļ
    -0.27
    ruz
    -0.27
    кÑĤ
    -0.25
     addTarget
    -0.25
    åIJįåı«
    -0.25
    驹
    -0.25
    Challenge
    -0.24
    YPE
    -0.24
    pons
    -0.24
    POSITIVE LOGITS
    _MPI
    0.30
    ä¸ĩè¾Ĩ
    0.27
    hex
    0.27
    åĮĸè¿Ľç¨ĭ
    0.25
    çģĮ
    0.25
    hub
    0.23
    gro
    0.23
    ogl
    0.23
    .Atomic
    0.23
    èģĶ缣
    0.23
    Activations Density 0.122%

    No Known Activations