© 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. 130175
    Prev
    Next
    INDEX
    Explanations

    code

    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
    agher
    -0.28
    åIJĦæĸ¹éĿ¢
    -0.27
    ukkit
    -0.27
    etration
    -0.26
    minster
    -0.26
    resh
    -0.25
    ãĢģ“
    -0.25
    lero
    -0.25
    pollo
    -0.25
    é¦ĸåħĪè¦ģ
    -0.24
    POSITIVE LOGITS
    缴
    0.28
    or
    0.28
    ft
    0.28
     buck
    0.28
    abe
    0.28
     Jude
    0.27
     sat
    0.27
    便
    0.26
    November
    0.26
    amente
    0.26
    Activations Density 0.009%

    No Known Activations