© 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. 19-TRANSCODER-HP
    7. 8590
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éļıæīĭ
    -0.28
    æĭ¿äºĨ
    -0.26
    .pair
    -0.26
    coil
    -0.25
    æĭ¿çĿĢ
    -0.25
    orado
    -0.25
    纪å§Ķ
    -0.25
    ĺ认
    -0.24
     tutor
    -0.24
    osi
    -0.24
    POSITIVE LOGITS
    åħĪ
    0.30
     Lama
    0.30
    æ³Ħ
    0.27
    åħĪè¡Į
    0.25
    åĸĦ
    0.24
     preceded
    0.24
     Dom
    0.23
    è¶ħè¿ĩ
    0.23
     CPL
    0.23
     DropIndex
    0.22
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.