© 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. 30-TRANSCODER-HP
    7. 96585
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鲸
    -0.28
    amac
    -0.27
    åºĬ
    -0.27
    èººåľ¨åºĬä¸Ĭ
    -0.27
    dest
    -0.27
    pin
    -0.26
    -pin
    -0.26
     pin
    -0.26
     bed
    -0.25
     connected
    -0.25
    POSITIVE LOGITS
    ei
    0.26
    ordo
    0.26
     dazz
    0.26
     orderby
    0.26
     Repair
    0.26
    icket
    0.24
     hes
    0.24
    äºī缸
    0.24
    essenger
    0.24
    orderid
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.