© 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. 88687
    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
    åħ¨æĹ¥
    -0.28
    泺
    -0.27
    Cur
    -0.25
     disciplines
    -0.25
    owns
    -0.25
     Discipline
    -0.25
    iras
    -0.24
    мо
    -0.24
    åŃIJå¼Ł
    -0.24
     Napoli
    -0.24
    POSITIVE LOGITS
    aped
    0.26
    gage
    0.25
    inged
    0.24
     emerg
    0.24
    .tpl
    0.23
    аÑĤегоÑĢ
    0.23
    åĬ³åĬ¡
    0.23
    èĪŀ
    0.23
     asking
    0.23
    æ¯Ĵ
    0.23
    Activations Density 1.277%

    No Known Activations

    This feature has no known activations.