© 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. 141939
    Prev
    Next
    INDEX
    Explanations

    ply

    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
     Reconstruction
    -0.28
    æŀĦæĪIJ
    -0.27
     Nom
    -0.26
    reme
    -0.25
    éĢı
    -0.25
     Mobile
    -0.24
     discrete
    -0.24
    迨
    -0.24
     nom
    -0.24
    emer
    -0.24
    POSITIVE LOGITS
    izedName
    0.28
    олÑĥÑĩ
    0.28
     somehow
    0.27
    edin
    0.26
    ariat
    0.25
    èµ°ä¸ĭåİ»
    0.25
    alink
    0.25
    è¾ķ
    0.25
    etter
    0.25
    ä¸ĭåİ»
    0.24
    Activations Density 4.396%

    No Known Activations