© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    Code snippets/special chars

    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
     series
    -0.29
    hal
    -0.27
    ploy
    -0.26
    series
    -0.25
     model
    -0.25
    udes
    -0.25
    oten
    -0.25
    pons
    -0.24
     descri
    -0.24
    weets
    -0.24
    POSITIVE LOGITS
    alto
    0.25
    æķıæĦŁ
    0.25
    è´¨éĩıåĴĮ
    0.25
    Fox
    0.25
    stell
    0.25
    åıĹ害èĢħ
    0.24
    Jackson
    0.24
    å¥ij约
    0.24
     ÑģÑĤо
    0.23
    Ÿ
    0.23
    Activations Density 0.051%

    No Known Activations