© 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. 8522
    Prev
    Next
    INDEX
    Explanations

    URL paths

    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
    affer
    -0.27
     BrowserModule
    -0.27
    utzer
    -0.27
    PageSize
    -0.27
    åıįæŃ£
    -0.26
     ******************************************************************************↵
    -0.26
    jong
    -0.25
     klass
    -0.25
    åı¤äºº
    -0.24
    lobber
    -0.24
    POSITIVE LOGITS
     lip
    0.27
     correl
    0.27
    oval
    0.26
     combination
    0.26
     wzglÄĻd
    0.26
     Lip
    0.25
    .misc
    0.25
    åIJĬ
    0.25
    æ¹¾
    0.25
    æĢĢ念
    0.24
    Activations Density 0.020%

    No Known Activations