© 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. 7724
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å¤ĸéĿ¢
    -0.28
    irector
    -0.28
    Kid
    -0.26
    å®ļå±ħ
    -0.26
    /static
    -0.26
    afe
    -0.26
     raining
    -0.26
    å¤ĸçķĮ
    -0.26
    (static
    -0.26
    leaning
    -0.25
    POSITIVE LOGITS
    ece
    0.28
    æĢİä¹Īåģļ
    0.27
    çijķçĸµ
    0.26
    è¿Ŀæ³ķè¡Į为
    0.25
    å¤ļ人
    0.25
    \Validator
    0.24
     Lomb
    0.24
    è´ŁåĢº
    0.23
     Hastings
    0.23
    оÑģÑĤÑĮÑİ
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.