© 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. 8281
    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
     licence
    -0.26
     metres
    -0.26
     licences
    -0.25
    çŁ³çģ°
    -0.25
     filesize
    -0.25
    |m
    -0.25
     Ev
    -0.25
    ä¸ĢéŨ
    -0.25
    ze
    -0.25
    .prob
    -0.25
    POSITIVE LOGITS
    émon
    0.29
    uzzi
    0.27
     Shepherd
    0.26
    eli
    0.26
     Starbucks
    0.25
     Scholar
    0.25
    unner
    0.25
    _fragment
    0.25
    æĶ¶è´¹æłĩåĩĨ
    0.24
    UND
    0.24
    Activations Density 0.114%

    No Known Activations

    This feature has no known activations.