© 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. 25-TRANSCODER-HP
    7. 107889
    Prev
    Next
    INDEX
    Explanations

    Data/internet context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     independent
    -0.28
     trials
    -0.27
     initially
    -0.27
     scarcely
    -0.26
     memory
    -0.26
     options
    -0.26
     potentially
    -0.25
    积åĪĨ
    -0.25
     memories
    -0.25
     right
    -0.25
    POSITIVE LOGITS
    å¨ĺ
    0.26
    rogram
    0.26
    ular
    0.25
    __/
    0.25
     Curriculum
    0.25
    cura
    0.24
    -uri
    0.24
    omain
    0.24
    ulation
    0.23
     erh
    0.23
    Activations Density 0.936%

    No Known Activations