© 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. 6245
    Prev
    Next
    INDEX
    Explanations

    Parts or quantities of something

    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
    enia
    -0.30
     remaining
    -0.29
    remaining
    -0.29
    Remaining
    -0.27
    åī©ä¸ĭçļĦ
    -0.27
    .remaining
    -0.27
     Remaining
    -0.26
    _remaining
    -0.26
     stickers
    -0.25
     selfies
    -0.25
    POSITIVE LOGITS
    alink
    0.27
    pany
    0.27
    ainer
    0.25
     pname
    0.25
    aviolet
    0.25
    æŁĶ
    0.25
     certain
    0.24
    cest
    0.24
     overlay
    0.24
    mark
    0.23
    Activations Density 0.007%

    No Known Activations