© 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. 12-TRANSCODER-HP
    7. 23259
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹Łä¸įçŁ¥éģĵ
    -0.31
     overloaded
    -0.27
     unspecified
    -0.27
    nic
    -0.27
     overhead
    -0.26
    .Lookup
    -0.25
    宦
    -0.24
    ä¹Łæ²¡æľī
    -0.24
    寡
    -0.24
    GroupName
    -0.24
    POSITIVE LOGITS
    ng
    0.27
    oton
    0.27
    ngen
    0.26
    urrent
    0.26
     payer
    0.26
    èĴĻ
    0.26
    ï¼ĮãĢĬ
    0.26
    çīį
    0.25
    urs
    0.25
    piece
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.