© 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. 89766
    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
    åįĬå²Ľ
    -0.26
    _caps
    -0.26
    æ¹ĸ
    -0.25
    ç§ijæķĻ
    -0.24
    Poll
    -0.24
    æ±
    -0.24
     Isles
    -0.24
    ogs
    -0.24
     Econom
    -0.24
    ủng
    -0.23
    POSITIVE LOGITS
    èµĺ
    0.33
    enal
    0.26
     Realt
    0.26
     Brid
    0.25
    渤
    0.25
    early
    0.24
     fore
    0.24
    éĢļè¿ĩ
    0.24
    å¿ħè¦ģ
    0.24
    ë°Ľ
    0.24
    Activations Density 1.319%

    No Known Activations

    This feature has no known activations.