© 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. 30-TRANSCODER-HP
    7. 95987
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardown
    -0.31
     supported
    -0.28
    ctl
    -0.27
    itori
    -0.27
    çŃı
    -0.26
    笳
    -0.26
     ownership
    -0.25
    .support
    -0.25
     Supported
    -0.25
    -Control
    -0.25
    POSITIVE LOGITS
    积累
    0.30
    æľĽ
    0.27
    积累äºĨ
    0.26
     definit
    0.26
    çģ¯åħī
    0.25
    æįIJåĬ©
    0.24
    æ²¹èĢĹ
    0.24
     Device
    0.24
    åĻ¨ä»¶
    0.24
    Device
    0.24
    Activations Density 0.886%

    No Known Activations