© 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. 19-TRANSCODER-HP
    7. 8179
    Prev
    Next
    INDEX
    Explanations

    ago

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨåĩł
    -0.27
    ä¸ĭåİ»
    -0.27
    ocomplete
    -0.26
    ering
    -0.26
    äºĨ许å¤ļ
    -0.26
    bed
    -0.26
    loff
    -0.25
    åĩ¹
    -0.25
    led
    -0.24
    äºĨ大éĩıçļĦ
    -0.24
    POSITIVE LOGITS
     seal
    0.26
     Won
    0.26
     influential
    0.26
    ÙĪاÙĨ
    0.26
     Vu
    0.25
     ages
    0.25
     lul
    0.24
     Ages
    0.23
    ä¹Łè¢«
    0.22
    Mr
    0.21
    Activations Density 1.747%

    No Known Activations