© 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. 53592
    Prev
    Next
    INDEX
    Explanations

    is

    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
    chen
    -0.28
    pan
    -0.28
    qual
    -0.27
    ep
    -0.26
    oms
    -0.26
    ith
    -0.26
    æĸĩçī©
    -0.26
    innen
    -0.26
    strap
    -0.26
    æĸ¹å¼ıè¿Ľè¡Į
    -0.26
    POSITIVE LOGITS
     certain
    0.44
    ä¸Ģå®ļçļĦ
    0.35
     Certain
    0.34
    ä¸Ģå®ļ
    0.32
    Certain
    0.32
     sur
    0.31
     certains
    0.30
    樵
    0.27
    thought
    0.27
    æŁIJäºĽ
    0.27
    Activations Density 0.019%

    No Known Activations