© 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. 98556
    Prev
    Next
    INDEX
    Explanations

    general text

    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
    人åĢij
    -0.25
     spells
    -0.24
    é¢¨æł¼
    -0.24
    roph
    -0.24
    åĽ½éģĵ
    -0.23
    .getSystemService
    -0.23
     Pars
    -0.23
     dec
    -0.23
    olon
    -0.23
    é²·
    -0.23
    POSITIVE LOGITS
     Identify
    0.28
     Attempt
    0.26
     Notice
    0.25
     ÑĢебен
    0.24
    å¸Ĥåľº
    0.24
    åĬŁ
    0.24
     CE
    0.24
     Publish
    0.24
     Overall
    0.24
    dı
    0.24
    Activations Density 0.011%

    No Known Activations