© 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. 5130
    Prev
    Next
    INDEX
    Explanations

    Punctuation for dates/code

    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
    subtype
    -0.32
    oting
    -0.28
    å¹ķåIJİ
    -0.27
    (expect
    -0.27
    æIJĶ
    -0.27
    -bars
    -0.26
    _variant
    -0.26
    herits
    -0.26
    UPI
    -0.25
    RectTransform
    -0.25
    POSITIVE LOGITS
    lia
    0.32
    eval
    0.31
    reg
    0.30
    rem
    0.30
    ira
    0.28
    çIJĨ
    0.28
     e
    0.28
    2
    0.27
     Reg
    0.27
    lá
    0.26
    Activations Density 0.022%

    No Known Activations