© 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. 96499
    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
    é»ī
    -0.27
    stakes
    -0.25
    幸
    -0.25
    计åħ¥
    -0.25
    astered
    -0.25
    æľ¦
    -0.25
    пÑĥÑģ
    -0.24
    àªĩ
    -0.24
    isted
    -0.24
    åħ³éŨ
    -0.23
    POSITIVE LOGITS
    continuous
    0.29
     Continuous
    0.29
    éĢ£çºĮ
    0.28
    è¿ŀç»Ń
    0.28
    ugu
    0.28
    íį¼
    0.26
    Continuous
    0.26
    没åħ³ç³»
    0.25
    ç¹ģå¿Ļ
    0.25
     continuous
    0.25
    Activations Density 0.881%

    No Known Activations

    This feature has no known activations.