© 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. 95903
    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
    ington
    -0.34
    /GPL
    -0.29
    æ¼Ķ
    -0.27
    积水
    -0.26
    éĺ²æ°´
    -0.25
    vat
    -0.25
    laus
    -0.24
    INGTON
    -0.24
    avl
    -0.24
    ï¼ģ↵↵↵↵
    -0.24
    POSITIVE LOGITS
    欲
    0.34
     want
    0.29
    prep
    0.25
     wants
    0.24
    pData
    0.24
     wish
    0.24
    AFF
    0.24
     desire
    0.24
    ä¹°
    0.23
    pill
    0.23
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.