© 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. 35-TRANSCODER-HP
    7. 38842
    Prev
    Next
    INDEX
    Explanations

    the ending "ene"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .ic
    -0.26
     va
    -0.25
    -winning
    -0.25
    ä¹ĭæĺŁ
    -0.24
     swept
    -0.24
     defeats
    -0.24
    omat
    -0.23
    _HPP
    -0.23
    _DIRECTORY
    -0.23
    .va
    -0.23
    POSITIVE LOGITS
    enne
    0.32
    eni
    0.31
    itarian
    0.30
    ettes
    0.30
    enes
    0.30
    ça
    0.30
    enso
    0.29
    orum
    0.29
    eny
    0.29
    eness
    0.29
    Activations Density 0.084%

    No Known Activations