© 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. 7033
    Prev
    Next
    INDEX
    Explanations

    cow, ranch

    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
     wsp
    -0.28
    踵
    -0.25
    æ°ĶåĢĻåıĺåĮĸ
    -0.23
     Halo
    -0.23
    alsy
    -0.22
    мÑı
    -0.22
    ence
    -0.22
    WindowSize
    -0.22
    RIA
    -0.22
     NOI
    -0.21
    POSITIVE LOGITS
    adt
    0.27
    ields
    0.24
    eron
    0.23
     AUTHORS
    0.23
    èµ·äºĨ
    0.23
    ining
    0.23
    ees
    0.22
    ä¸ĢæŶ
    0.22
     masses
    0.22
    err
    0.22
    Activations Density 2.341%

    No Known Activations