© 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. 20-TRANSCODER-HP
    7. 107393
    Prev
    Next
    INDEX
    Explanations

    Education finance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoot
    -0.28
    Åĭ
    -0.28
    ercul
    -0.27
    èĥ½åĬĽåĴĮ
    -0.26
    -Mobile
    -0.26
    ãģ°
    -0.26
    oping
    -0.25
    chte
    -0.24
    PING
    -0.24
    ancode
    -0.24
    POSITIVE LOGITS
    å®ĥçļĦ
    0.29
    keh
    0.27
    eh
    0.27
    èį£
    0.25
    è¿Ļç§įæĥħåĨµ
    0.25
    oose
    0.25
    èĢĮæĺ¯
    0.24
    æ¶īåıĬ
    0.24
    ured
    0.24
    æ¶īåıĬåĪ°
    0.24
    Activations Density 5.043%

    No Known Activations