© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88312
    Prev
    Next
    INDEX
    Explanations

    power, influence, control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç«ł
    -0.32
    没åħ³ç³»
    -0.27
    esh
    -0.26
    çĦī
    -0.26
    æĬķ
    -0.26
    å²ģæŶ
    -0.25
    lectron
    -0.24
     obr
    -0.24
     sez
    -0.24
    çŀ¬
    -0.24
    POSITIVE LOGITS
    foot
    0.27
    erm
    0.26
     report
    0.25
     peaked
    0.25
    powered
    0.24
    ãģĦãģŁãģłãģĦãģŁ
    0.24
    -report
    0.24
    ãģĦãģŁãģłãģijãĤĭ
    0.24
    енÑĤа
    0.24
     critical
    0.23
    Activations Density 9.310%

    No Known Activations