© 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. 89851
    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
    á¿ĸ
    -0.30
    LocalizedString
    -0.27
    %i
    -0.25
    åij¨æľ«
    -0.25
    oner
    -0.24
    {})
    -0.24
    å¼ĢéĢļ
    -0.24
     ëĵ
    -0.24
     rer
    -0.24
    ...)
    -0.24
    POSITIVE LOGITS
    edin
    0.27
    ìłģìĿ´
    0.26
    ory
    0.25
    ãģ£ãģ±
    0.25
    ave
    0.25
    andel
    0.24
    andler
    0.24
    ently
    0.24
     quotient
    0.24
    é³į
    0.23
    Activations Density 2.330%

    No Known Activations

    This feature has no known activations.