© 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. 108489
    Prev
    Next
    INDEX
    Explanations

    Mixed technical context

    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
    éĢIJ
    -0.38
    äº¤æĽ¿
    -0.35
     successive
    -0.34
     repeatedly
    -0.34
    éļıçĿĢ
    -0.33
     continually
    -0.33
    ä¸įæĸŃ
    -0.33
     continuously
    -0.32
    allel
    -0.31
     repeated
    -0.31
    POSITIVE LOGITS
    两年åīį
    0.30
    ä¸ĢåĪĨéĴ±
    0.28
    enk
    0.28
    åŃĺéĩı
    0.27
    ä¸Ĭ次
    0.27
    XmlNode
    0.27
    iben
    0.26
    åıijæĸĩ
    0.24
    baru
    0.24
    åĭŁéĽĨèµĦéĩij
    0.24
    Activations Density 1.034%

    No Known Activations