© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6340
    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
     erg
    -0.25
    æĪijå¦Ī
    -0.25
    ported
    -0.25
    å©´
    -0.25
    è¾ĸåĮº
    -0.24
     active
    -0.24
    grades
    -0.23
     multi
    -0.23
    ists
    -0.23
     Maher
    -0.23
    POSITIVE LOGITS
    NotFoundError
    0.27
    è¿ĻäºĽä¸ľè¥¿
    0.25
    客æľį
    0.25
    =pk
    0.24
    ebra
    0.24
    omencl
    0.24
    erializer
    0.24
    Convention
    0.24
    -che
    0.23
    èĢģå¸ĪçļĦ
    0.23
    Activations Density 0.205%

    No Known Activations

    This feature has no known activations.