© 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. 8180
    Prev
    Next
    INDEX
    Explanations

    buy or sell

    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
    [".
    -0.26
    çĸij
    -0.25
    /framework
    -0.25
    ][-
    -0.25
     negatives
    -0.25
     clearColor
    -0.24
    Optimizer
    -0.24
    ues
    -0.24
    æĸ°éĻĪ代谢
    -0.24
    æĬĹèıĮ
    -0.24
    POSITIVE LOGITS
    ä¹°äºĨ
    0.28
    æīĢåľ¨
    0.27
    æŶåĪ»
    0.26
    ä¹°
    0.26
    ä¸ĢåĪ»
    0.24
    åIJįå½ķ
    0.24
    订è´Ń
    0.24
    è¢ĸ
    0.24
     tomar
    0.24
    haar
    0.23
    Activations Density 0.004%

    No Known Activations