© 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. 30-TRANSCODER-HP
    7. 94920
    Prev
    Next
    INDEX
    Explanations

    Booking and reservation systems

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    注åĨĮ
    -0.92
     registration
    -0.90
     register
    -0.84
    æĬ¥åIJį
    -0.81
     registering
    -0.81
     registrations
    -0.81
     registr
    -0.77
    çĻ»è®°
    -0.75
     Register
    -0.75
    -register
    -0.74
    POSITIVE LOGITS
    æ´Ħ
    0.28
    å·¢
    0.27
    å¾Ĺèµ·
    0.27
    åIJĥåĪ°
    0.27
     councils
    0.26
    åŁºåĩĨ
    0.25
    座è°Ī
    0.24
    çŃ·
    0.24
    åĢ¦
    0.24
    åģľå·¥
    0.23
    Activations Density 0.910%

    No Known Activations