© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88898
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    jerne
    -0.26
    å¥Ħ
    -0.25
    Ìģ
    -0.24
    ัว
    -0.24
    ç®±
    -0.24
    æģ°
    -0.24
    åĨįéĢł
    -0.24
     {
    -0.23
    é¹ŀ
    -0.23
     account
    -0.23
    POSITIVE LOGITS
    avings
    0.34
     iceberg
    0.28
     Minist
    0.28
     ministries
    0.28
    bst
    0.28
     derivative
    0.25
    _ios
    0.25
    æ¯ĴæĢ§
    0.24
     deriv
    0.24
     ministry
    0.23
    Activations Density 0.296%

    No Known Activations

    This feature has no known activations.