© 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. 25-TRANSCODER-HP
    7. 107114
    Prev
    Next
    INDEX
    Explanations

    N

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    omaly
    -0.29
    exus
    -0.28
    æĤį
    -0.28
     Universal
    -0.27
    umeric
    -0.27
     Ghost
    -0.26
    Universal
    -0.26
    avigation
    -0.26
    nection
    -0.26
    ihar
    -0.25
    POSITIVE LOGITS
    greg
    0.25
    loth
    0.24
    ç´ĭ
    0.24
    loon
    0.24
    两项
    0.24
     ips
    0.23
    cord
    0.23
    èĻĶ
    0.23
     alone
    0.23
    gre
    0.23
    Activations Density 1.007%

    No Known Activations