© 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. 130221
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
    积累
    -0.30
    oub
    -0.27
    cum
    -0.26
    ixmap
    -0.26
    ço
    -0.25
    éļį
    -0.25
     cres
    -0.24
    nap
    -0.24
    å°ı康
    -0.24
     Cum
    -0.24
    POSITIVE LOGITS
    使èĢħ
    0.29
    设ç«ĭäºĨ
    0.27
     Accepted
    0.27
    /Branch
    0.26
    _dispatcher
    0.26
    odyn
    0.26
    structor
    0.25
    éĵ
    0.25
    æĦıæĢĿ
    0.25
     arbitr
    0.24
    Activations Density 0.241%

    No Known Activations