© 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. 22-TRANSCODER-HP
    7. 112400
    Prev
    Next
    INDEX
    Explanations

    variation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olio
    -0.29
    isha
    -0.26
    iens
    -0.24
    oric
    -0.23
    encial
    -0.23
    oit
    -0.23
    Cli
    -0.22
    éķĿ
    -0.22
    icans
    -0.22
    ause
    -0.22
    POSITIVE LOGITS
     frequency
    0.27
     Min
    0.27
     wild
    0.26
    ware
    0.26
     circumstances
    0.25
     minim
    0.24
     capital
    0.24
    vented
    0.24
    ä¸ĩåįĥ
    0.24
    å¾Ĺå¾Ī
    0.24
    Activations Density 0.136%

    No Known Activations