© 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. 9040
    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
    æľīäºĽ
    -0.29
    è¿ĻçĤ¹
    -0.27
    æİĴè¡Į
    -0.26
    ¦Ĥ
    -0.24
    TableRow
    -0.24
    Ni
    -0.24
    gee
    -0.24
    äºĽä»Ģä¹Ī
    -0.24
    aan
    -0.23
    quite
    -0.23
    POSITIVE LOGITS
     rap
    0.27
    åĭ¾
    0.26
    ilty
    0.25
    emes
    0.24
    éĴĿ
    0.24
    èĥ¨
    0.24
    olia
    0.24
    亢
    0.24
    lig
    0.23
    riday
    0.23
    Activations Density 0.126%

    No Known Activations

    This feature has no known activations.