© 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. 27-TRANSCODER-HP
    7. 9595
    Prev
    Next
    INDEX
    Explanations

    Technical writing passages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    就被
    -0.30
    |array
    -0.28
    éķ°
    -0.27
    hek
    -0.27
    被æīĵ
    -0.27
    被åĪ¤
    -0.26
    AMA
    -0.25
     neighb
    -0.25
     Adler
    -0.24
    dock
    -0.24
    POSITIVE LOGITS
    使çĶ¨çļĦ
    0.32
    æıIJåĩºçļĦ
    0.32
     undertake
    0.31
    éĿ¢ä¸´çļĦ
    0.26
    åģļçļĦäºĭæĥħ
    0.26
     gost
    0.26
     kidding
    0.26
     impose
    0.26
    usal
    0.26
    ẹ
    0.26
    Activations Density 0.058%

    No Known Activations