© 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. 107691
    Prev
    Next
    INDEX
    Explanations

    incomplete sentences

    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
     unique
    -0.29
    çĭ¬æľīçļĦ
    -0.29
    ucha
    -0.29
    mits
    -0.28
    åĶ¯ä¸ĢçļĦ
    -0.28
     Unique
    -0.27
     mistake
    -0.27
    误
    -0.27
    误ä¼ļ
    -0.27
    Unique
    -0.26
    POSITIVE LOGITS
    çļĦçIJĨ解
    0.28
    .nl
    0.28
    æĦıè¯ĨåĪ°
    0.28
     considerations
    0.27
    è¿ĺæĺ¯è¦ģ
    0.27
    é¢ĦåĪ¶
    0.26
    èĢĥèĻijåĪ°
    0.26
    .kr
    0.25
     maxWidth
    0.25
    dater
    0.25
    Activations Density 1.571%

    No Known Activations