© 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. 8741
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    olith
    -0.27
    .BASELINE
    -0.26
    åĵĪå°Ķ
    -0.26
    lemen
    -0.25
    Portal
    -0.25
    åĨ²åĬ¨
    -0.25
     Rhodes
    -0.25
    åħ¨äº§ä¸ļéĵ¾
    -0.25
    è¶Ĭ好
    -0.24
    äºĴè¡¥
    -0.24
    POSITIVE LOGITS
    è´¹
    0.27
    jur
    0.25
    Bug
    0.25
     ФедеÑĢ
    0.24
    FER
    0.24
    FE
    0.24
    ãĥľãĥ¼ãĥī
    0.24
     bugs
    0.23
    为ä¸Ńå¿ĥ
    0.23
     Isa
    0.23
    Activations Density 0.005%

    No Known Activations