© 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. 38829
    Prev
    Next
    INDEX
    Explanations

    Detects word endings

    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
    nt
    -0.35
    name
    -0.35
    l
    -0.35
    link
    -0.34
    n
    -0.34
    light
    -0.33
    lib
    -0.32
    nv
    -0.32
    line
    -0.32
    lit
    -0.32
    POSITIVE LOGITS
    cies
    0.45
    cy
    0.42
    cial
    0.38
    cence
    0.37
    ci
    0.35
    cie
    0.35
    cé
    0.35
    cia
    0.35
    cis
    0.32
    cion
    0.31
    Activations Density 27.325%

    No Known Activations