© 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. 106913
    Prev
    Next
    INDEX
    Explanations

    Before

    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
    ;<
    -0.30
    .tar
    -0.27
    æĸĹ
    -0.26
    ead
    -0.25
    egan
    -0.25
    .DE
    -0.25
    ubits
    -0.24
    ayer
    -0.24
    lemetry
    -0.24
    /de
    -0.24
    POSITIVE LOGITS
     Vers
    0.26
    è§Ĵ度çľĭ
    0.25
     Responsibility
    0.25
    åIJİæĤĶ
    0.24
     Refuge
    0.24
    æľīæĿĥ
    0.24
    èĤ©
    0.23
     единÑģÑĤв
    0.23
    .viewDidLoad
    0.23
    knife
    0.23
    Activations Density 0.109%

    No Known Activations