© 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. 43377
    Prev
    Next
    INDEX
    Explanations

    the

    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
     first
    -1.23
     First
    -1.13
    First
    -1.10
    first
    -1.09
    _first
    -1.04
    第ä¸Ģ个
    -1.03
     FIRST
    -1.01
    é¦ĸ个
    -1.01
    çļĦ第ä¸Ģ
    -1.01
    第ä¸Ģ
    -1.00
    POSITIVE LOGITS
    äº
    0.23
    ibli
    0.23
    OKEN
    0.23
    ject
    0.22
    uetooth
    0.22
    äter
    0.22
    rotein
    0.21
    ARK
    0.21
    arness
    0.21
     midst
    0.21
    Activations Density 0.006%

    No Known Activations