© 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. 108628
    Prev
    Next
    INDEX
    Explanations

    adjectives describing states

    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
    ä»ĸçļĦ
    -0.39
    æĤ¨çļĦ
    -0.39
    ä½łçļĦ
    -0.37
    å®ĥçļĦ
    -0.35
    ä»ĸ们çļĦ
    -0.35
    äºĨä»ĸçļĦ
    -0.34
    åħ¶
    -0.33
    æł¹æį®èĩªå·±
    -0.33
     Ñģвоего
    -0.31
    åħ¶æīĢ
    -0.31
    POSITIVE LOGITS
    orm
    0.28
    {'
    0.25
    æĿ¡è¯Ħ论
    0.24
    eng
    0.24
    èĢIJ
    0.24
    线ä¸ĭ
    0.24
     thoughts
    0.23
     Shot
    0.23
    被æīĵ
    0.23
     ordinary
    0.23
    Activations Density 1.179%

    No Known Activations