© 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. 24-TRANSCODER-HP
    7. 149719
    Prev
    Next
    INDEX
    Explanations

    Python programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     composing
    -0.35
    à¹Īà¸Ń
    -0.30
    Compose
    -0.30
     legalized
    -0.29
     legalize
    -0.29
     compose
    -0.29
     composition
    -0.29
    Composition
    -0.28
    åıĸè¯ģ
    -0.28
     narration
    -0.27
    POSITIVE LOGITS
    python
    0.37
    Python
    0.36
     programming
    0.35
     Python
    0.35
    ç¼ĸç¨ĭ
    0.33
     coding
    0.32
    programming
    0.32
     programmers
    0.32
     python
    0.32
     code
    0.32
    Activations Density 0.920%

    No Known Activations