© 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. 40530
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and codes

    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
    çĸ¾çĹħçļĦ
    -0.29
    çī¹èī²
    -0.28
    kid
    -0.27
    ooks
    -0.27
     Prime
    -0.26
    年第
    -0.26
    (Card
    -0.25
    shelf
    -0.25
    upil
    -0.25
    éĽı
    -0.25
    POSITIVE LOGITS
     caut
    0.34
    avic
    0.29
    RAD
    0.29
    acc
    0.29
    ADB
    0.27
    ARI
    0.27
    EC
    0.27
    adoo
    0.27
    ec
    0.27
     behind
    0.27
    Activations Density 0.076%

    No Known Activations