© 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. 5095
    Prev
    Next
    INDEX
    Explanations

    Blitz

    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
     Sly
    -0.26
     agreeing
    -0.25
    ÙĤر
    -0.24
    .Keys
    -0.23
     bride
    -0.23
    traffic
    -0.23
     gov
    -0.23
    à¬ī
    -0.23
    -hidden
    -0.23
    kest
    -0.23
    POSITIVE LOGITS
    éĵ¾
    0.29
    çªĴ
    0.27
    (tm
    0.27
    èĦĤ
    0.25
    ç¥ĸåĽ½
    0.25
    æŁ´
    0.24
    die
    0.23
    .credentials
    0.23
    /power
    0.23
    ationToken
    0.23
    Activations Density 0.932%

    No Known Activations