© 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. 23795
    Prev
    Next
    INDEX
    Explanations

    translation

    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
     mat
    -0.28
    åģı
    -0.26
    seek
    -0.25
    èĬ
    -0.25
    (#)
    -0.25
    æīĢ
    -0.25
    å·
    -0.25
    iew
    -0.24
    个
    -0.24
    ATIC
    -0.24
    POSITIVE LOGITS
     Stretch
    0.27
     Fälle
    0.27
    åĸīåĴĻ
    0.27
    /stretch
    0.26
    reibung
    0.26
    æĢĿãģĦåĩº
    0.25
     stretch
    0.25
     distracted
    0.24
     stuffing
    0.24
    ä¸Ģå®ļèĥ½
    0.24
    Activations Density 0.001%

    No Known Activations