© 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. 25-TRANSCODER-HP
    7. 107940
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liner
    -0.24
    cen
    -0.24
    çµķå°į
    -0.24
    åĩºåİ»
    -0.24
    onn
    -0.24
    .backends
    -0.24
    ä¸Ģèµ·
    -0.23
    æĢ»éĩı
    -0.23
    wei
    -0.23
    åIJįåı«
    -0.23
    POSITIVE LOGITS
    åIJĦ个æĸ¹éĿ¢
    0.34
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.31
    foil
    0.27
    å¾Īå¤ļäºĭæĥħ
    0.27
     iss
    0.27
    genome
    0.27
    æĸ¹æĸ¹éĿ¢
    0.27
    ildo
    0.26
     their
    0.26
     aspects
    0.26
    Activations Density 0.132%

    No Known Activations