© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7545
    Prev
    Next
    INDEX
    Explanations

    studies, research, management

    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
    atel
    -0.26
     Increases
    -0.25
    Increases
    -0.25
    éĴĩ
    -0.25
    atorio
    -0.24
    åİŁåŃIJ
    -0.24
    æĹ¥çĽĬ
    -0.24
    atorium
    -0.23
    setName
    -0.23
     setActive
    -0.23
    POSITIVE LOGITS
    etes
    0.29
    æIJ¬åĪ°
    0.29
    æĿ¥çļĦ
    0.28
    æݨ
    0.26
     hers
    0.26
     squeezed
    0.26
     squeeze
    0.25
    rees
    0.25
    è´Ł
    0.25
    ines
    0.24
    Activations Density 0.015%

    No Known Activations