© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107716
    Prev
    Next
    INDEX
    Explanations

    Comparisons and opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .+
    -0.28
     Inf
    -0.28
     Struct
    -0.26
    matched
    -0.25
    æīįè¡Į
    -0.25
    åıĮè¾¹
    -0.25
    ccion
    -0.25
    ibil
    -0.25
    (ib
    -0.24
    ’s
    -0.24
    POSITIVE LOGITS
     canv
    0.29
    SCALE
    0.27
     viewBox
    0.25
     PACKAGE
    0.25
    çīĪæĿĥ声æĺİ
    0.24
    è°Ī
    0.24
    oot
    0.24
     substrate
    0.23
    usk
    0.23
     system
    0.23
    Activations Density 44.569%

    No Known Activations