© 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. 8719
    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
    æŁIJ
    -0.26
    æĬ¥éģĵ称
    -0.26
    é»ijæļĹ
    -0.26
    æ°´å¹³
    -0.26
    åĪĨéĴŁåIJİ
    -0.25
    è¿ĩçļĦ
    -0.25
     Gone
    -0.25
    ervatives
    -0.24
    å±Ĭæ¯ķä¸ļçĶŁ
    -0.24
    IVEN
    -0.24
    POSITIVE LOGITS
     catch
    0.26
    (cli
    0.25
    uese
    0.25
    orest
    0.25
     cle
    0.24
     Mob
    0.23
    clusion
    0.23
    agation
    0.23
     Swe
    0.23
     Material
    0.23
    Activations Density 0.484%

    No Known Activations

    This feature has no known activations.