© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107256
    Prev
    Next
    INDEX
    Explanations

    Web page text

    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
    çļĦä¸Ģ款
    -0.31
    odef
    -0.28
    azar
    -0.27
    åı¦ä¸Ģç§į
    -0.27
    ừng
    -0.26
    ocker
    -0.26
    iêu
    -0.25
    OnError
    -0.24
    人为
    -0.24
    endtime
    -0.23
    POSITIVE LOGITS
     %{
    0.28
    enze
    0.27
    jit
    0.26
    chia
    0.25
    >+
    0.25
     hic
    0.25
    avis
    0.25
    家éķ¿ä»¬
    0.24
    ä¸ĭæĿ¥
    0.23
    è¦ĨçĽĸ
    0.23
    Activations Density 0.958%

    No Known Activations