© 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. 18-TRANSCODER-HP
    7. 88482
    Prev
    Next
    INDEX
    Explanations

    Programming, symbols, mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vocabulary
    -0.26
    massage
    -0.26
    NB
    -0.25
     Frontier
    -0.24
    FOX
    -0.24
    åİŁæĸĩ
    -0.23
    rush
    -0.23
    ä½Ī
    -0.23
     ham
    -0.23
    tam
    -0.23
    POSITIVE LOGITS
    áµ
    0.25
    à¹īà¸Ń
    0.25
     sik
    0.25
     поÑģледние
    0.24
     `_
    0.23
    ä»Ģä¹Īäºĭ
    0.23
    ik
    0.23
    él
    0.23
     {_
    0.23
    pendicular
    0.23
    Activations Density 12.577%

    No Known Activations