© 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. 95877
    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
    ÇIJ
    -0.28
    ÄŃ
    -0.27
    ihu
    -0.27
    åĨįåĬłä¸Ĭ
    -0.26
    |#
    -0.25
    /tests
    -0.24
    ock
    -0.24
    luet
    -0.24
    _subtype
    -0.23
    hua
    -0.23
    POSITIVE LOGITS
    edin
    0.27
    æĻ¨
    0.27
    arak
    0.25
    foil
    0.24
    actic
    0.24
     mistaken
    0.24
     jej
    0.24
    ])]↵
    0.23
    éĶĻè¿ĩäºĨ
    0.23
    jes
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.