© 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. 58118
    Prev
    Next
    INDEX
    Explanations

    code related text

    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
    ä»»
    -0.30
     things
    -0.28
     mix
    -0.27
    dt
    -0.26
    bury
    -0.25
     facts
    -0.24
    amar
    -0.24
     tried
    -0.24
    asti
    -0.24
    äºĭçī©
    -0.24
    POSITIVE LOGITS
    溢
    0.27
    èĢĮåĩº
    0.27
    åħ¨ä½ĵåijĺå·¥
    0.26
    çĦ°
    0.24
    çļĦ强大
    0.24
     mitig
    0.24
    -tooltip
    0.24
    ÃĹ↵↵
    0.24
     Mit
    0.24
    .ops
    0.23
    Activations Density 0.002%

    No Known Activations