© 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. 40555
    Prev
    Next
    INDEX
    Explanations

    Code/Technical text

    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
    Negative Logits
    éªĹåıĸ
    -0.27
    copies
    -0.26
    å°Ĩåľ¨
    -0.25
    éªĹ
    -0.25
    侧éĩį
    -0.25
    åįıåĬŀ
    -0.24
     Crit
    -0.24
    å¼Ģå°ģ
    -0.23
    èĨº
    -0.23
    è°ĥæݧ
    -0.23
    POSITIVE LOGITS
    isu
    0.32
    ees
    0.30
    erras
    0.30
    erm
    0.29
    ered
    0.28
    lard
    0.28
    orde
    0.28
    ord
    0.28
    eam
    0.27
    anness
    0.27
    Activations Density 0.065%

    No Known Activations