© 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. 109139
    Prev
    Next
    INDEX
    Explanations

    Numerical data and codes

    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
    èIJ¥ä¸ļ
    -0.32
    çļĦéĤ£ä¸Ģ
    -0.29
     confirmed
    -0.28
    æł¸
    -0.28
    ç¡®
    -0.27
     therapists
    -0.27
    lef
    -0.27
    legt
    -0.26
    confirmed
    -0.26
     confirming
    -0.25
    POSITIVE LOGITS
    ickets
    0.28
    å¤ı天
    0.27
    ulan
    0.26
    æĮĩçĤ¹
    0.26
    locks
    0.25
     incompatible
    0.25
     FML
    0.25
    çĻ»
    0.25
    éªŀ
    0.24
    "]."
    0.24
    Activations Density 0.885%

    No Known Activations