© 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. 8617
    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
     succeeding
    -0.29
    æ°ª
    -0.29
    odable
    -0.26
    acky
    -0.26
    æī¾åĩĨ
    -0.25
    hosts
    -0.25
    ROID
    -0.24
    åŃľ
    -0.24
    Connell
    -0.24
    æľĪä¸Ń
    -0.24
    POSITIVE LOGITS
     Riding
    0.31
    ries
    0.30
     semantics
    0.28
    æĬ¼
    0.28
    å°Ħ
    0.28
    TOT
    0.28
     b
    0.27
    èĮĥçķ´
    0.27
    æī«
    0.26
     div
    0.26
    Activations Density 3.317%

    No Known Activations

    This feature has no known activations.