© 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. 89082
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    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
    stime
    -0.28
     masses
    -0.28
    æijĩ
    -0.28
    Ñīа
    -0.27
    éħįä¸Ĭ
    -0.26
    æIJĸ
    -0.26
     BaseActivity
    -0.26
    æķ°éĩı
    -0.25
    .baidu
    -0.24
    ä¸ºåŁºç¡Ģ
    -0.24
    POSITIVE LOGITS
    cretion
    0.28
    .property
    0.28
     kn
    0.27
     grantResults
    0.26
    åĪ°åºķ
    0.25
     Kn
    0.25
     Graham
    0.24
    agens
    0.24
     KN
    0.24
    orton
    0.24
    Activations Density 19.244%

    No Known Activations