© 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. 40615
    Prev
    Next
    INDEX
    Explanations

    scientific/legal documents

    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
    cr
    -0.35
    MR
    -0.32
    afari
    -0.31
    aar
    -0.31
     NR
    -0.31
    Cr
    -0.30
     MR
    -0.30
    kr
    -0.30
    CR
    -0.29
    chw
    -0.29
    POSITIVE LOGITS
    åİŁåĪĻ
    0.34
     princ
    0.31
     princip
    0.28
     promot
    0.27
    ìĻķ
    0.25
    fork
    0.25
     principle
    0.25
     Shack
    0.24
    软
    0.24
    MESS
    0.24
    Activations Density 2.420%

    No Known Activations