© 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. 30-TRANSCODER-HP
    7. 95836
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ForObject
    -0.26
    acle
    -0.25
     zaman
    -0.24
    ä¸ĵ享
    -0.24
    åŀĭ
    -0.24
     visita
    -0.24
     Totally
    -0.24
     Clients
    -0.23
    xmm
    -0.23
    å¦ŀ
    -0.23
    POSITIVE LOGITS
    é»Ħéĩij
    0.27
     sal
    0.26
     pre
    0.26
    feit
    0.26
     rect
    0.26
     lim
    0.25
     extended
    0.25
     account
    0.25
     parenthesis
    0.25
    boxed
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.