© 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. 89263
    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
    canf
    -0.30
    peria
    -0.27
    Pont
    -0.26
     tats
    -0.26
    ADS
    -0.26
    ónico
    -0.26
    éĶ¶
    -0.25
    /rest
    -0.24
    è¿Ķè¿ĺ
    -0.24
    atable
    -0.24
    POSITIVE LOGITS
    ë¶Ī
    0.24
    HL
    0.24
    æ¡ĮéĿ¢
    0.24
    $criteria
    0.24
     Æ¡n
    0.24
    ooth
    0.23
    åĩ«
    0.23
    å°ģ建
    0.23
     emiss
    0.23
    åħ¬ä¸»
    0.23
    Activations Density 26.051%

    No Known Activations

    This feature has no known activations.