© 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. 22-TRANSCODER-HP
    7. 112068
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /OR
    -0.30
    rientation
    -0.27
    åĨħå¤ĸ
    -0.27
     domestic
    -0.27
    OTION
    -0.26
    æĪĸå°Ĩ
    -0.26
     mListener
    -0.26
    rait
    -0.26
     cog
    -0.25
    åIJĦç±»
    -0.25
    POSITIVE LOGITS
     Bug
    0.26
    -tank
    0.24
    owe
    0.24
     stages
    0.23
    'value
    0.23
     pressed
    0.23
    åħ¨æł¡
    0.23
    веÑĢÑħ
    0.23
     guns
    0.23
    -Trump
    0.23
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.