© 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. 20-TRANSCODER-HP
    7. 63651
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸĩä¸Ń
    -0.25
     Gamb
    -0.24
    ivityManager
    -0.24
    éĿŀ常çļĦ
    -0.24
    ached
    -0.24
    ohana
    -0.24
     sane
    -0.23
    oh
    -0.23
    ices
    -0.23
    èĬĴæŀľ
    -0.23
    POSITIVE LOGITS
     maxim
    0.30
     minim
    0.28
    å°±è¡Į
    0.26
     coinc
    0.25
    æijĩ头
    0.25
    æĢĢ
    0.25
    çļĦåĵģçīĮ
    0.25
    uck
    0.24
    åĨį说
    0.24
    Through
    0.24
    Activations Density 22.416%

    No Known Activations