© 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. 19-TRANSCODER-HP
    7. 8995
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    vla
    -0.26
    umas
    -0.25
    岫
    -0.24
     Aub
    -0.24
    oba
    -0.24
    .Optional
    -0.23
     vibrations
    -0.23
    ⾦
    -0.23
    \"\
    -0.23
    osta
    -0.23
    POSITIVE LOGITS
    éĤ£æŶåĢĻ
    0.27
    è¦ģä¸įçĦ¶
    0.27
     conf
    0.25
    patial
    0.24
    éĤ£ä¸ªæŶåĢĻ
    0.24
    ลà¸Ńย
    0.23
    etest
    0.23
    PHONE
    0.23
    éĤ£æŶ
    0.23
    åºĶ该
    0.22
    Activations Density 3.110%

    No Known Activations