© 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. 95415
    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
    **/↵
    -0.27
    upil
    -0.26
    ä¸įæŃ¢
    -0.25
     Ebook
    -0.25
    wald
    -0.24
     withheld
    -0.24
    (stop
    -0.24
     IMPLIED
    -0.24
    uren
    -0.23
    stadt
    -0.23
    POSITIVE LOGITS
    iance
    0.32
    æ³Ľ
    0.31
    严
    0.30
    éĻIJæŶ
    0.29
    ä½ľä¸º
    0.29
    ermo
    0.29
    path
    0.29
    éĻĨ
    0.27
    xFE
    0.27
    imate
    0.27
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.