© 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. 54540
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    pecies
    -0.26
     diffuse
    -0.26
     fluid
    -0.25
    models
    -0.25
     WB
    -0.24
     block
    -0.24
     hé
    -0.24
    eya
    -0.24
     drawer
    -0.24
    wb
    -0.24
    POSITIVE LOGITS
    om
    0.40
    ом
    0.32
    omet
    0.31
    ä¸ļ
    0.29
    ome
    0.27
     setC
    0.27
    oze
    0.27
    okus
    0.26
     om
    0.26
    омÑĥ
    0.25
    Activations Density 0.003%

    No Known Activations