© 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. 5071
    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
    鼷
    -0.25
     Apprec
    -0.25
    NotFoundError
    -0.24
    еÑģÑĤв
    -0.24
    æŀIJ
    -0.24
    åIJİèĢħ
    -0.24
    æľį
    -0.24
     dernier
    -0.24
    Refreshing
    -0.24
     refreshed
    -0.23
    POSITIVE LOGITS
    mdl
    0.32
    agna
    0.28
    locks
    0.27
    uther
    0.27
    DAC
    0.26
    éļ¶å±ŀäºİ
    0.26
    iets
    0.26
     locks
    0.25
    æīĵéĢłåĩº
    0.25
    deen
    0.25
    Activations Density 0.174%

    No Known Activations

    This feature has no known activations.