© 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. 6593
    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
     Believe
    -0.28
    转载
    -0.27
    èijĨ
    -0.26
     Congratulations
    -0.25
    çħĮ
    -0.25
    åħ¥åľº
    -0.24
    eme
    -0.24
     Offer
    -0.24
    itives
    -0.24
    åħ¬ä¼Ĺåı·
    -0.24
    POSITIVE LOGITS
     buses
    0.27
     pedals
    0.26
    Rails
    0.25
    :variables
    0.25
    æľªå¿ħ
    0.25
     sober
    0.25
    .Axis
    0.25
     bus
    0.24
     waves
    0.24
    morph
    0.24
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.