© 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. 18-TRANSCODER-HP
    7. 89304
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.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¸įå¼Ģ
    -0.28
    deep
    -0.28
    éĩįå·¥
    -0.26
    etrics
    -0.25
    åħ»èĤ²
    -0.24
    EFR
    -0.24
    bum
    -0.24
    ventory
    -0.24
     Pok
    -0.23
    ypass
    -0.23
    POSITIVE LOGITS
    æİĴæĸ¥
    0.30
     ing
    0.26
     who
    0.26
    io
    0.26
     plus
    0.24
    IC
    0.24
    æĭĴ
    0.24
    -human
    0.23
     way
    0.23
    (io
    0.23
    Activations Density 21.296%

    No Known Activations