© 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. 57052
    Prev
    Next
    INDEX
    Explanations

    code and math formulas

    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
    itten
    -0.29
    -blind
    -0.27
     sider
    -0.25
    å®ŀè·µä¸Ń
    -0.25
    éĩijèŀįç§ijæĬĢ
    -0.24
     obl
    -0.24
    æ¯Ķçİĩ
    -0.24
    autoload
    -0.24
    å®ŀè·µ
    -0.24
     resisted
    -0.24
    POSITIVE LOGITS
     base
    0.28
     duplicate
    0.27
    unn
    0.27
    dbg
    0.26
     basis
    0.26
    åŁº
    0.26
     bases
    0.25
    æłĩåĩĨ
    0.25
     niche
    0.25
    uv
    0.25
    Activations Density 0.003%

    No Known Activations