© 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. 52757
    Prev
    Next
    INDEX
    Explanations

    -st

    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
    edImage
    -0.35
    eds
    -0.29
    ders
    -0.27
    estone
    -0.27
    ä¸Ńæĸĩ
    -0.26
    enas
    -0.26
     distilled
    -0.26
    _extended
    -0.26
    alty
    -0.26
    ets
    -0.26
    POSITIVE LOGITS
    oven
    0.33
    cow
    0.26
    fall
    0.25
    åĨħ容ç®Ģä»ĭ
    0.25
     shown
    0.25
    shown
    0.24
    ]<<
    0.24
    çį¸
    0.24
    wid
    0.24
    æĶ¯
    0.23
    Activations Density 0.006%

    No Known Activations