© 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. 31-TRANSCODER-HP
    7. 19178
    Prev
    Next
    INDEX
    Explanations

    than

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .TimeUnit
    -0.27
    æĹĭ
    -0.27
    dee
    -0.26
    å°ıåŀĭ
    -0.26
    roke
    -0.25
    åŁŃ
    -0.25
    dpi
    -0.25
     Tyson
    -0.24
     viewer
    -0.24
    elle
    -0.24
    POSITIVE LOGITS
    about
    0.31
     your
    0.31
     about
    0.30
    apt
    0.28
    ane
    0.28
    奶ç²ī
    0.28
     About
    0.28
    pus
    0.26
     a
    0.26
    Sport
    0.26
    Activations Density 0.796%

    No Known Activations