© 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. 88811
    Prev
    Next
    INDEX
    Explanations

    conclusions, finality

    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
    ç®ĢåĮĸ
    -0.26
    áticas
    -0.26
     skeletal
    -0.26
    qrst
    -0.25
     Rule
    -0.25
    utherland
    -0.25
     Boost
    -0.25
    .Normalize
    -0.24
    æĺ¼
    -0.24
     userInfo
    -0.24
    POSITIVE LOGITS
    vez
    0.26
    çļĦéĢļçŁ¥
    0.26
    issant
    0.26
    à°Ĺ
    0.25
    cripts
    0.25
     contre
    0.25
    åŀ
    0.24
    express
    0.24
    Ñĥй
    0.24
    ovan
    0.24
    Activations Density 13.050%

    No Known Activations