© 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. 90055
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    ž
    -0.25
    ideo
    -0.25
    hem
    -0.24
    enu
    -0.24
     succ
    -0.23
     Equipment
    -0.23
    elli
    -0.23
    ireccion
    -0.23
     Recover
    -0.23
    åłĨ
    -0.23
    POSITIVE LOGITS
    ently
    0.41
    æ¶ī
    0.28
    lers
    0.28
    称
    0.27
    itations
    0.27
     =(
    0.26
    angs
    0.26
    Touches
    0.25
    ter
    0.25
     childs
    0.24
    Activations Density 20.177%

    No Known Activations