© 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. 89235
    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
    annonce
    -0.28
     Dez
    -0.25
    .Claims
    -0.25
    azor
    -0.24
    ä¸įæĩĪ
    -0.24
    ocities
    -0.23
     ç¬
    -0.23
     Increment
    -0.23
    énom
    -0.23
    chunk
    -0.23
    POSITIVE LOGITS
     agent
    0.26
    ished
    0.26
    )n
    0.25
    èķ²
    0.24
    (py
    0.24
    .house
    0.24
    æ¼Ĥ
    0.24
    Ñĩе
    0.23
    ди
    0.23
    director
    0.23
    Activations Density 3.813%

    No Known Activations

    This feature has no known activations.