© 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. 7015
    Prev
    Next
    INDEX
    Explanations

    and

    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
    çIJĨ解åĴĮ
    -0.30
    ç»ıéªĮåĴĮ
    -0.27
    ivist
    -0.27
    æŶéĹ´åĴĮ
    -0.26
     Bri
    -0.25
    andra
    -0.25
    ä½łå¥½
    -0.25
    ä¼ģä¸ļåĴĮ
    -0.24
     nonetheless
    -0.23
    .Err
    -0.23
    POSITIVE LOGITS
    èĶ¼
    0.27
    ç½ijéĢļ
    0.25
     stimulate
    0.25
    .addTo
    0.25
    reas
    0.25
    âĬĦ
    0.24
    alus
    0.24
    ftime
    0.23
    å°Ĭ严
    0.23
    _pin
    0.23
    Activations Density 0.408%

    No Known Activations