© 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. 43645
    Prev
    Next
    INDEX
    Explanations

    code

    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
    $$
    -0.72
     $$
    -0.63
    .$$
    -0.41
    ãĢŁ
    -0.39
    "↵↵
    -0.37
    )":
    -0.37
    ãĢī
    -0.35
    ãĢį
    -0.33
    ",↵
    -0.33
    ãĢı
    -0.32
    POSITIVE LOGITS
    .`
    0.95
    `
    0.94
    `,
    0.89
    :`
    0.85
    `↵
    0.85
     `
    0.85
     `↵
    0.82
    `.
    0.81
    `↵↵
    0.79
    `č↵
    0.79
    Activations Density 0.002%

    No Known Activations