© 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. 33-TRANSCODER-HP
    7. 54091
    Prev
    Next
    INDEX
    Explanations

    Gen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ers
    -0.27
    uge
    -0.27
    ram
    -0.26
    uffman
    -0.26
    ertime
    -0.24
    APER
    -0.24
    ogens
    -0.24
    åĦ¿
    -0.24
    azine
    -0.24
    aking
    -0.23
    POSITIVE LOGITS
     society
    0.31
     Society
    0.31
    社ä¼ļ
    0.29
     اÙĦعÙĦÙĬا
    0.24
    byter
    0.24
    collector
    0.23
    åīįæĻ¯
    0.23
    侦
    0.23
    oil
    0.22
    foil
    0.22
    Activations Density 0.016%

    No Known Activations