© 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. 7697
    Prev
    Next
    INDEX
    Explanations

    Code and news snippets

    np_max-act · gemini-2.0-flash
    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
    acies
    -0.27
     Aggregate
    -0.24
    _hashes
    -0.24
    nown
    -0.24
    èģļåIJĪ
    -0.23
    aggregate
    -0.23
    ernels
    -0.23
    èļĤèļģ
    -0.23
    è¦ģä¹Ī
    -0.23
    åħ®
    -0.23
    POSITIVE LOGITS
    æ¸
    0.25
    çļĦåħ³éĶ®
    0.25
    åİļ
    0.24
    Dear
    0.23
    amen
    0.23
    å°½
    0.23
    ä¹Łå°Ĩ
    0.23
     midway
    0.23
    éļ¾
    0.23
     Dart
    0.23
    Activations Density 0.009%

    No Known Activations