© 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. 18278
    Prev
    Next
    INDEX
    Explanations

    code

    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
    夹
    -0.31
    æĸĻ
    -0.29
    éĩį
    -0.28
    ắt
    -0.27
    cor
    -0.26
     sk
    -0.26
    çݰ代åĮĸ
    -0.26
    åĩĿ
    -0.26
     sm
    -0.26
     per
    -0.26
    POSITIVE LOGITS
    ikon
    0.28
    witch
    0.26
     dut
    0.26
    naires
    0.25
    ç³ĸæŀľ
    0.25
     expanding
    0.25
    :System
    0.24
     Insert
    0.24
     Inserts
    0.24
    sville
    0.23
    Activations Density 1.606%

    No Known Activations