© 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. 18-TRANSCODER-HP
    7. 89241
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®Į
    -0.32
    éĢIJ
    -0.30
    vo
    -0.26
    éĢIJä¸Ģ
    -0.25
    âu
    -0.25
     détail
    -0.24
    ä¾Ŀ次
    -0.24
     combineReducers
    -0.24
    ailand
    -0.23
    å®Įæķ´
    -0.23
    POSITIVE LOGITS
    åĬ¨èĥ½
    0.28
    ابة
    0.27
    .restart
    0.25
    igrated
    0.25
    èĭ±éĽĦ
    0.24
    ker
    0.23
    erot
    0.23
    ä¸įç®¡ä½ł
    0.23
    @Xml
    0.23
     pet
    0.23
    Activations Density 25.888%

    No Known Activations