© 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. 6727
    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
    éĨĴ缮
    -0.29
    å°ģ
    -0.26
    ável
    -0.26
    ikel
    -0.26
    å®ķ
    -0.25
     sage
    -0.24
     Kosten
    -0.24
    atorial
    -0.24
    gemÃ¤ÃŁ
    -0.24
     experiments
    -0.24
    POSITIVE LOGITS
     Scroll
    0.28
    achs
    0.25
    çĸ½
    0.25
    æĥħ
    0.25
     trợ
    0.24
     Ach
    0.24
     Barth
    0.23
    oader
    0.23
    èººåľ¨åºĬä¸Ĭ
    0.23
    ç¹ģèį£
    0.23
    Activations Density 0.307%

    No Known Activations

    This feature has no known activations.