© 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. 35-TRANSCODER-HP
    7. 39958
    Prev
    Next
    INDEX
    Explanations

    government agency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    math
    -0.29
    娱ä¹IJ
    -0.29
    æķ°åѦ
    -0.28
    æķĻèĤ²
    -0.28
    aus
    -0.27
     giải
    -0.27
    åĮĸåѦ
    -0.27
    åĪ¶ä½ľ
    -0.27
    解
    -0.27
    ://
    -0.27
    POSITIVE LOGITS
     Caught
    0.33
     Charges
    0.31
     Appointment
    0.31
     Presents
    0.30
     Wants
    0.29
     Covered
    0.29
     Charging
    0.29
     Presidency
    0.28
     Produced
    0.28
     Shelf
    0.28
    Activations Density 7.808%

    No Known Activations