© 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. 87667
    Prev
    Next
    INDEX
    Explanations

    Licenses

    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
     Counts
    -0.23
     Battles
    -0.23
    akest
    -0.23
     Yoshi
    -0.23
     Leader
    -0.22
    xygen
    -0.22
    neath
    -0.22
     Dresses
    -0.22
     Donation
    -0.22
    utches
    -0.22
    POSITIVE LOGITS
    c
    0.25
    i
    0.24
     res
    0.23
    åĵ¿
    0.22
     conv
    0.22
     lasting
    0.22
    o
    0.22
    ·
    0.22
    2
    0.21
     highlighted
    0.21
    Activations Density 0.371%

    No Known Activations