© 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. 53459
    Prev
    Next
    INDEX
    Explanations

    Academics and researchers

    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
    仨
    -0.28
    å·²ä¹ħ
    -0.27
    ĽĦ
    -0.27
    æ±ģ
    -0.26
    æłĩå¿ĹçĿĢ
    -0.26
     few
    -0.25
    è·ijåİ»
    -0.24
    Few
    -0.24
    -Clause
    -0.23
    forcer
    -0.23
    POSITIVE LOGITS
     researchers
    0.31
     Researchers
    0.29
     professors
    0.28
     labs
    0.28
     Files
    0.28
     Dr
    0.28
     Scient
    0.28
    ROL
    0.28
     families
    0.28
     files
    0.27
    Activations Density 0.138%

    No Known Activations