© 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. 12-TRANSCODER-HP
    7. 23625
    Prev
    Next
    INDEX
    Explanations

    ruption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponder
    -0.31
     powers
    -0.29
    eva
    -0.28
    powers
    -0.28
    avian
    -0.26
    lee
    -0.26
     Powers
    -0.26
    .Dom
    -0.25
     ÄIJình
    -0.25
    eam
    -0.24
    POSITIVE LOGITS
     ccp
    0.27
    棵
    0.27
    ë§ī
    0.26
     Bentley
    0.25
     Jackets
    0.25
    okit
    0.25
    å¥ĹæĪ¿
    0.24
    _cpus
    0.24
    ès
    0.24
    <Map
    0.23
    Activations Density 0.001%

    No Known Activations