© 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. 22-TRANSCODER-HP
    7. 87391
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accept
    -0.28
     file
    -0.28
    atl
    -0.26
    ats
    -0.26
    влек
    -0.25
    веÑģ
    -0.25
     satisf
    -0.25
    ural
    -0.25
     adopt
    -0.25
    CPP
    -0.25
    POSITIVE LOGITS
    è¿ijè·Ŀ离
    0.27
    otine
    0.26
     DEVICE
    0.26
     Fuck
    0.25
    -device
    0.25
    主æĮģ
    0.24
    /device
    0.24
     Sesso
    0.24
    _device
    0.23
    aks
    0.23
    Activations Density 0.016%

    No Known Activations