© 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. 32-TRANSCODER-HP
    7. 43256
    Prev
    Next
    INDEX
    Explanations

    Networking, computer hardware

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ward
    -0.34
     strategist
    -0.26
    wards
    -0.26
     alum
    -0.25
     ward
    -0.25
     den
    -0.24
     wards
    -0.24
     Lake
    -0.24
    LOG
    -0.24
     Sweden
    -0.24
    POSITIVE LOGITS
    æ²¹èĦĤ
    0.30
    æIJº
    0.28
    VPN
    0.27
     kvm
    0.27
     KV
    0.26
    _vp
    0.26
     ITE
    0.25
     ASM
    0.25
     Gim
    0.25
    éºĿ
    0.25
    Activations Density 0.013%

    No Known Activations