© 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. 29730
    Prev
    Next
    INDEX
    Explanations

    process

    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
    çłģ
    -0.28
    iji
    -0.27
     she
    -0.27
    atas
    -0.27
    quare
    -0.26
    åĽ½äºº
    -0.26
    åŀ£
    -0.25
    æĬ¤
    -0.25
    èŃ·
    -0.25
    colo
    -0.24
    POSITIVE LOGITS
    çŃ¹çłģ
    0.27
    uren
    0.27
     PACKAGE
    0.27
    otted
    0.27
    é«ĵ
    0.24
    ä¸Ĭ线
    0.24
    åĶ¾
    0.24
    -capital
    0.24
     Re
    0.24
    ден
    0.24
    Activations Density 1.463%

    No Known Activations