© 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. 31-TRANSCODER-HP
    7. 19127
    Prev
    Next
    INDEX
    Explanations

    code and copyright notices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ¢äºİ
    -0.30
    éĹ»
    -0.27
     Filename
    -0.27
    pector
    -0.25
    ä¸ľè¥¿
    -0.25
    NamedQuery
    -0.25
    ยว
    -0.25
    Grace
    -0.25
    shan
    -0.24
    ä¸Ŀè·¯
    -0.23
    POSITIVE LOGITS
     feeder
    0.28
    arium
    0.28
    heim
    0.27
    hg
    0.27
    hed
    0.27
    cente
    0.27
    éĽĨä¸Ń
    0.27
    iture
    0.27
    holm
    0.26
     springs
    0.26
    Activations Density 0.004%

    No Known Activations