© 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. 9005
    Prev
    Next
    INDEX
    Explanations

    technical/military contexts

    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
    æĪ·å¤ĸ
    -0.29
     interface
    -0.28
    æıŃéľ²
    -0.28
    ä¸įèµ·
    -0.27
     interaction
    -0.27
     interactions
    -0.27
    髦
    -0.27
     uptake
    -0.26
     interfaces
    -0.26
    /stats
    -0.26
    POSITIVE LOGITS
    微信åı·
    0.29
    窥
    0.27
    è¡Įç¨ĭ
    0.26
    Watcher
    0.26
    aqu
    0.26
    office
    0.25
    (PHP
    0.25
    каж
    0.25
    emoth
    0.25
     Headquarters
    0.25
    Activations Density 0.023%

    No Known Activations