© 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. 12-TRANSCODER-HP
    7. 23311
    Prev
    Next
    INDEX
    Explanations

    scaling and resizing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izin
    -0.26
    åįķ项
    -0.25
     frontal
    -0.25
    llvm
    -0.24
    ikip
    -0.24
     Hy
    -0.24
    åīį沿
    -0.24
     présente
    -0.24
     vinden
    -0.23
    éŁĤ
    -0.23
    POSITIVE LOGITS
    缩
    0.35
    scaling
    0.34
    缩å°ı
    0.34
    åĢį
    0.32
    æĶ¾å¤§
    0.30
    稳
    0.30
    metatable
    0.29
    Scaling
    0.29
     scaling
    0.29
     Resize
    0.28
    Activations Density 0.003%

    No Known Activations