© 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. 30010
    Prev
    Next
    INDEX
    Explanations

    Netflix, germ

    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
    åĨĻä¸ĭ
    -0.28
    æĮīä¸ĭ
    -0.25
    西çıŃ
    -0.25
     dispro
    -0.24
    ymax
    -0.24
    uala
    -0.24
    .compose
    -0.24
    ])**
    -0.24
    Tpl
    -0.24
    /background
    -0.24
    POSITIVE LOGITS
    omination
    0.28
    MessageType
    0.27
     Sark
    0.27
    ä»ĺ
    0.27
     premiere
    0.26
    shed
    0.26
    _atoms
    0.25
    NodeType
    0.24
    agnostics
    0.24
     STUD
    0.24
    Activations Density 0.416%

    No Known Activations