© 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. 108128
    Prev
    Next
    INDEX
    Explanations

    Code comments and posts

    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
    mol
    -0.27
    lug
    -0.26
    Current
    -0.26
    =current
    -0.26
    umped
    -0.25
     current
    -0.25
    æĪį
    -0.25
    current
    -0.25
    横
    -0.25
    gate
    -0.24
    POSITIVE LOGITS
    并ä¸į
    0.30
    ä¸Ŀ毫ä¸į
    0.28
    并éĿŀ
    0.27
    并æĹł
    0.26
    没åħ³ç³»
    0.25
    éĻĤ
    0.24
     asn
    0.24
     Deg
    0.23
    并ä¸įèĥ½
    0.23
    没æľī太大
    0.23
    Activations Density 2.760%

    No Known Activations