© 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. 7300
    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
    reach
    -0.27
    Keeper
    -0.26
     fin
    -0.26
    bury
    -0.24
    ião
    -0.24
    onte
    -0.24
     kite
    -0.24
    ðŁĵIJ
    -0.23
    KD
    -0.23
    KL
    -0.23
    POSITIVE LOGITS
    æ°ijæĹı
    0.29
    æĺ¼å¤ľ
    0.27
    Ê°
    0.27
     fizz
    0.27
    shal
    0.26
    æŶéĹ´åĴĮ
    0.25
     primaryKey
    0.24
    -muted
    0.24
    accent
    0.24
    è±ķ
    0.24
    Activations Density 0.048%

    No Known Activations

    This feature has no known activations.