© 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. 54821
    Prev
    Next
    INDEX
    Explanations

    W. or William or Wilhelm

    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
    peria
    -0.28
    YC
    -0.28
     Front
    -0.28
    åº
    -0.27
    ween
    -0.27
    .front
    -0.26
    Front
    -0.26
    åłij
    -0.26
    åIJĨ
    -0.26
    èµ°è¿ij
    -0.25
    POSITIVE LOGITS
    uite
    0.27
    pard
    0.26
    顺
    0.25
    right
    0.24
    uit
    0.24
    ("#{
    0.23
    ç®Ń
    0.23
    ело
    0.23
    ncia
    0.23
     Pag
    0.23
    Activations Density 0.008%

    No Known Activations