© 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. 7574
    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
    çļĦæķħäºĭ
    -0.28
    Const
    -0.26
    erna
    -0.25
    ampaign
    -0.25
     impunity
    -0.25
     consts
    -0.24
    ç»ĪçĶŁ
    -0.24
    辩è¯ģ
    -0.24
    å¡ijéĢł
    -0.24
    indi
    -0.23
    POSITIVE LOGITS
    odox
    0.30
    å°ij
    0.28
    溥
    0.27
    转移åĪ°
    0.27
    oque
    0.27
    oi
    0.25
     menn
    0.25
    thin
    0.24
    çªĿ
    0.24
     ?><?
    0.24
    Activations Density 0.041%

    No Known Activations

    This feature has no known activations.