© 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. 35-TRANSCODER-HP
    7. 40776
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iore
    -0.30
    .loads
    -0.28
    IAM
    -0.28
    ÙĬÙĪÙħ
    -0.28
    ä¸į容
    -0.27
    iem
    -0.27
    ilver
    -0.27
    便æ°ij
    -0.26
     imposed
    -0.25
    increase
    -0.25
    POSITIVE LOGITS
    atica
    0.46
    ctal
    0.43
    atics
    0.38
    atti
    0.38
    atic
    0.36
    ATT
    0.35
    att
    0.35
    atal
    0.34
    atar
    0.34
    tti
    0.34
    Activations Density 0.030%

    No Known Activations