© 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. 52528
    Prev
    Next
    INDEX
    Explanations

    say "numbers"

    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
    asi
    -0.25
    Reality
    -0.25
    åİ¿åħ¬å®īå±Ģ
    -0.24
    廨
    -0.24
    æ¯Ľ
    -0.24
    evin
    -0.24
     cre
    -0.23
    .decorate
    -0.23
    ibili
    -0.23
    Cre
    -0.23
    POSITIVE LOGITS
    åįģä¸ĥ
    0.32
     thirteen
    0.31
     twelve
    0.28
    tw
    0.28
     eleven
    0.28
     fifteen
    0.27
    åįģäºĮ
    0.27
    éĹ´
    0.27
    twenty
    0.26
    æĭĽ
    0.26
    Activations Density 0.015%

    No Known Activations