© 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. 18896
    Prev
    Next
    INDEX
    Explanations

    code and non-english tokens

    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
    iece
    -0.30
    âĹĦ
    -0.26
    insula
    -0.25
     WEIGHT
    -0.25
    gio
    -0.25
    idon
    -0.25
     <<↵
    -0.25
    idal
    -0.24
     новоÑģÑĤи
    -0.24
     QText
    -0.24
    POSITIVE LOGITS
    å®ŀè´¨
    0.31
    åĶĩ
    0.29
    up
    0.28
     Rath
    0.27
    红
    0.26
     life
    0.26
    ael
    0.26
    åī¯
    0.25
    åłĨ积
    0.25
    life
    0.25
    Activations Density 0.013%

    No Known Activations