© 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. 29887
    Prev
    Next
    INDEX
    Explanations

    ene

    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
    红è±Ĩ
    -0.25
    exion
    -0.24
     thù
    -0.24
    gan
    -0.23
    _fact
    -0.23
    fact
    -0.23
    seen
    -0.23
    ',{↵
    -0.23
     fact
    -0.23
     stack
    -0.23
    POSITIVE LOGITS
     Injectable
    0.27
    =forms
    0.26
    oger
    0.26
    lÃŃ
    0.26
    TableName
    0.25
    AVA
    0.25
    èĴĻ
    0.25
    .rawValue
    0.24
    -original
    0.24
    JAVA
    0.24
    Activations Density 1.888%

    No Known Activations