© 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. 23-TRANSCODER-HP
    7. 24605
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļ
    -0.30
    åľ¨
    -0.29
    z
    -0.28
    åıĪ
    -0.28
    orum
    -0.28
    Entre
    -0.28
    ä¸Ģ个
    -0.28
    ”
    -0.27
    æĬ«
    -0.27
    马
    -0.27
    POSITIVE LOGITS
    幡
    0.28
    åIJ¦åīĩ
    0.26
    _LOGGER
    0.26
    pisa
    0.25
    å·²å®ĮæĪIJ
    0.25
    acha
    0.25
    iterated
    0.25
    ehr
    0.25
    æīįæĺ¯çľŁæŃ£
    0.25
    rapper
    0.25
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.