© 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. 42611
    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
    ım
    -0.27
     Bottom
    -0.25
    .imp
    -0.25
     Impress
    -0.25
    ople
    -0.24
    enever
    -0.24
    olley
    -0.24
    _topology
    -0.23
    غاÙĦ
    -0.23
    imet
    -0.23
    POSITIVE LOGITS
     event
    0.42
    äºĭ件
    0.35
    event
    0.34
    -event
    0.31
    Event
    0.31
    	event
    0.30
    deen
    0.29
     Event
    0.29
    .event
    0.29
    =event
    0.29
    Activations Density 0.004%

    No Known Activations