© 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. 20-TRANSCODER-HP
    7. 107449
    Prev
    Next
    INDEX
    Explanations

    _prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬĬæĪij
    -0.25
    æĶ¾ä¸ĭ
    -0.24
    aturity
    -0.24
    太å°ij
    -0.24
    {}{↵
    -0.23
    junction
    -0.23
     enqueue
    -0.23
     creo
    -0.23
    hap
    -0.23
     drops
    -0.22
    POSITIVE LOGITS
    act
    0.28
    ewise
    0.27
    astic
    0.27
    edly
    0.26
    æĪı
    0.26
    perc
    0.25
     chron
    0.25
     audits
    0.25
    sec
    0.25
    acted
    0.25
    Activations Density 0.603%

    No Known Activations