© 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. 6716
    Prev
    Next
    INDEX
    Explanations

    Understanding

    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
     *.
    -0.27
    ()._
    -0.25
    .pb
    -0.25
     pragma
    -0.25
     ei
    -0.25
     agre
    -0.24
    .inf
    -0.24
     con
    -0.24
    åĩºå¤Ħ
    -0.24
    ]._
    -0.23
    POSITIVE LOGITS
    äºĨä»ĸçļĦ
    0.27
    oval
    0.26
    adero
    0.25
     pilgr
    0.24
    olin
    0.24
    _MESH
    0.24
    acos
    0.24
    ckt
    0.24
    梦
    0.24
     treffen
    0.24
    Activations Density 0.079%

    No Known Activations