© 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. 9-TRANSCODER-HP
    7. 29925
    Prev
    Next
    INDEX
    Explanations

    young

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mission
    -0.29
    èľĩ
    -0.27
    èĮĨ
    -0.26
     Hodg
    -0.26
    czy
    -0.24
    ç»ĵå®ŀ
    -0.24
    .getRoot
    -0.24
    chts
    -0.24
    utta
    -0.23
     mission
    -0.23
    POSITIVE LOGITS
    å·¥ç¨ĭé¡¹çĽ®
    0.28
    åĮ»çĸĹæľįåĬ¡
    0.28
    +x
    0.27
    estar
    0.26
     newObj
    0.26
     locales
    0.25
    EqualTo
    0.25
     locality
    0.25
    庸
    0.24
    Auto
    0.24
    Activations Density 0.226%

    No Known Activations