© 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. 23134
    Prev
    Next
    INDEX
    Explanations

    single letters

    np_max-act · gemini-2.0-flash
    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
    iram
    -0.26
    fork
    -0.26
    è±¢
    -0.26
    ixin
    -0.25
    (ix
    -0.25
    åĩºæĿ¥äºĨ
    -0.24
    imore
    -0.24
     createDate
    -0.23
    èħĶ
    -0.23
    icc
    -0.23
    POSITIVE LOGITS
    ãĤĤãģªãģĦ
    0.28
    -hide
    0.27
     décou
    0.27
    :hidden
    0.26
    dden
    0.25
    å§Ķç»Ħç»ĩéĥ¨
    0.24
    feb
    0.24
    fortawesome
    0.24
    -items
    0.24
     widest
    0.24
    Activations Density 0.028%

    No Known Activations