© 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. 20-TRANSCODER-HP
    7. 107537
    Prev
    Next
    INDEX
    Explanations

    Food preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atives
    -0.33
    æĻĭ
    -0.28
    ogui
    -0.27
    alcon
    -0.26
     alb
    -0.26
     penn
    -0.25
    íĿ¥
    -0.25
    poon
    -0.24
    /native
    -0.24
    omon
    -0.24
    POSITIVE LOGITS
    aux
    0.30
    æµĪ
    0.28
    åĨį说
    0.27
    clerosis
    0.25
    åĬŁåĬ³
    0.24
    åıĮåıĮ
    0.24
     Yok
    0.24
    éal
    0.23
    _wo
    0.23
    resh
    0.23
    Activations Density 12.641%

    No Known Activations