© 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. 24-TRANSCODER-HP
    7. 149864
    Prev
    Next
    INDEX
    Explanations

    Uncommon terms and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othy
    -0.27
    .gwt
    -0.26
    客æĪ·æıIJä¾Ľ
    -0.25
     ker
    -0.25
    ework
    -0.25
     hus
    -0.24
     Probe
    -0.24
     Apprentice
    -0.24
     rehears
    -0.24
    çĻ»éĮĦ
    -0.24
    POSITIVE LOGITS
    ¼
    0.28
    åĩºèĩª
    0.28
    åŃĹ
    0.26
    spark
    0.26
     Carly
    0.24
    loyd
    0.24
    æľīçļĦ
    0.24
     пÑĢавиÑĤелÑĮ
    0.24
     rem
    0.24
    itional
    0.23
    Activations Density 0.002%

    No Known Activations