© 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. 27-TRANSCODER-HP
    7. 57807
    Prev
    Next
    INDEX
    Explanations

    Code/audio processing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distortion
    -0.35
     distort
    -0.32
    łģ
    -0.29
     artifacts
    -0.29
     Stark
    -0.28
    shake
    -0.27
    å³°åĢ¼
    -0.27
    漫
    -0.27
     Artifact
    -0.27
     shake
    -0.27
    POSITIVE LOGITS
    æĭ¬
    0.29
     farmers
    0.28
    isses
    0.26
    pond
    0.26
    åį«
    0.26
    acc
    0.26
    toolbar
    0.25
    åĨ·åĨ·
    0.25
    -widgets
    0.25
    ç¢į
    0.25
    Activations Density 0.012%

    No Known Activations