© 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. 7981
    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
    ç¦Ħ
    -0.31
    &E
    -0.30
    hos
    -0.27
    å¾Ĵ
    -0.27
    _eth
    -0.25
    æĪIJæľ¬
    -0.25
    afs
    -0.24
    _reporting
    -0.24
    akov
    -0.24
    åįļ
    -0.23
    POSITIVE LOGITS
    Parcel
    0.28
    åıijå±ķæľºéģĩ
    0.26
     Parm
    0.26
    æĻĤãģ®
    0.25
     ed
    0.25
    presso
    0.24
     syll
    0.24
    å¿ĥåĬ¨
    0.24
    owied
    0.23
    ThreadId
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.