© 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. 27-TRANSCODER-HP
    7. 9040
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    metro
    -0.28
    说åĩº
    -0.24
     stability
    -0.23
    IEW
    -0.23
    稳å®ļæĢ§
    -0.23
    FFE
    -0.23
    æ°ĶåĢĻ
    -0.23
    ResponseStatus
    -0.23
    mium
    -0.23
    GES
    -0.23
    POSITIVE LOGITS
    sist
    0.28
    bles
    0.26
    filtr
    0.25
    ä¾µçĬ¯
    0.25
    æĸĹ
    0.25
    姿
    0.25
    iece
    0.23
    褰
    0.23
    apore
    0.23
    ä¸įäºĨ
    0.23
    Activations Density 0.001%

    No Known Activations