© 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. 9-TRANSCODER-HP
    7. 29825
    Prev
    Next
    INDEX
    Explanations

    winning or advancement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃĹåı·
    -0.26
     âĨĴ
    -0.26
    âĨĴ
    -0.26
    Om
    -0.25
    ovich
    -0.25
    annel
    -0.24
    lad
    -0.24
    å¹ħ度
    -0.24
    estroy
    -0.24
    ä¸Ģè½®
    -0.23
    POSITIVE LOGITS
    å½ķåıĸ
    0.28
    ART
    0.26
    enk
    0.25
    çĽij管
    0.25
    _capacity
    0.24
    iage
    0.24
    ä¸ŃåѦ
    0.24
    irc
    0.24
    çįĦ
    0.24
    ë¡ł
    0.24
    Activations Density 1.760%

    No Known Activations