© 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. 54504
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Not in Any Lists

    No Comments

    Negative Logits
    jest
    -0.30
    å½
    -0.27
    åĬ²
    -0.26
    REFER
    -0.25
    stras
    -0.25
    ms
    -0.24
    rac
    -0.24
    mö
    -0.24
     Jeżeli
    -0.24
    angan
    -0.24
    POSITIVE LOGITS
    ington
    0.27
     Island
    0.26
     Cycle
    0.25
     fal
    0.25
     Level
    0.25
    çī¢
    0.24
    cycle
    0.24
    nqu
    0.24
    Cycle
    0.24
    à¸Ľà¸²à¸ģ
    0.23
    Activations Density 0.004%

    No Known Activations