© 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. 32-TRANSCODER-HP
    7. 43002
    Prev
    Next
    INDEX
    Explanations

    Code and formal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èį§
    -0.26
    çŃĴ
    -0.26
    çŁ¿çī©è´¨
    -0.26
     Bea
    -0.25
    RYPT
    -0.24
    ertil
    -0.24
    umer
    -0.24
     dep
    -0.24
    .Dep
    -0.23
     posing
    -0.23
    POSITIVE LOGITS
    ä¸Ģ个èģĮä¸ļ
    0.27
    ãĢħ
    0.26
    æĹłäºº
    0.25
    å½ĵåľ°äºº
    0.25
    heets
    0.25
    å½ĵåľ°çļĦ
    0.24
    åĦ¿
    0.24
    ots
    0.24
    åħĴ
    0.24
     //~
    0.23
    Activations Density 0.000%

    No Known Activations