© 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. 33-TRANSCODER-HP
    7. 54632
    Prev
    Next
    INDEX
    Explanations

    places and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aic
    -0.26
    主æĦı
    -0.26
    sim
    -0.26
    ç§ģä¸ĭ
    -0.26
    å±Ģ
    -0.25
     switched
    -0.24
    åĮħ裹
    -0.24
    ıs
    -0.24
    systems
    -0.23
    иков
    -0.23
    POSITIVE LOGITS
    endent
    0.28
     round
    0.26
     лиÑĨа
    0.26
    WND
    0.26
    å½»
    0.25
    ombat
    0.25
     amount
    0.25
    lements
    0.25
     Round
    0.24
    lettes
    0.24
    Activations Density 0.181%

    No Known Activations