© 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. 7118
    Prev
    Next
    INDEX
    Explanations

    Single character

    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
     mount
    -0.28
     kur
    -0.26
    秩
    -0.25
     ngo
    -0.25
    Mont
    -0.25
     Mont
    -0.24
     Bit
    -0.24
    ç½ijåıĭè¯Ħ论
    -0.24
     Index
    -0.24
     punch
    -0.24
    POSITIVE LOGITS
    iffin
    0.26
    çī©ç§į
    0.25
    æĹ¢èĥ½
    0.25
    raham
    0.25
    QRST
    0.25
    ayah
    0.25
    cran
    0.24
    uding
    0.24
    éĨĴ
    0.24
    _criteria
    0.24
    Activations Density 0.005%

    No Known Activations