© 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. 96170
    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
     Buzz
    -0.27
    严
    -0.26
    å¹²
    -0.26
    crud
    -0.25
    mond
    -0.25
     typename
    -0.25
    ä¸İæѤ
    -0.25
    åħ¸
    -0.25
    erno
    -0.24
    ½æķ°
    -0.24
    POSITIVE LOGITS
    ç«ĭ项
    0.29
    inode
    0.26
    èĢģå¸ĪçļĦ
    0.26
    _inode
    0.25
     springs
    0.24
    alyzer
    0.24
    tics
    0.24
    zyst
    0.24
    aminer
    0.24
    pine
    0.24
    Activations Density 0.940%

    No Known Activations

    This feature has no known activations.