© 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. 89345
    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
    éĢ¸
    -0.27
    å¼ķ
    -0.27
    ç´¯äºĨ
    -0.26
    èIJ¥
    -0.26
    ä¸ļ
    -0.26
    question
    -0.25
     question
    -0.25
    uste
    -0.25
    зов
    -0.24
    ”?
    -0.24
    POSITIVE LOGITS
    好åĩłä¸ª
    0.30
    аÑĨиÑİ
    0.28
     freshness
    0.27
    .Criteria
    0.25
    æ®ĭå¿į
    0.25
    trä
    0.25
    antz
    0.24
    azes
    0.24
    Chance
    0.24
    modele
    0.23
    Activations Density 0.488%

    No Known Activations

    This feature has no known activations.