© 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. 89010
    Prev
    Next
    INDEX
    Explanations

    technical/scientific writing

    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
    èĬ
    -0.26
    duto
    -0.26
    ueur
    -0.26
    irim
    -0.25
     Sheet
    -0.24
    หม
    -0.24
    ephy
    -0.24
    åŃ½
    -0.24
     sheet
    -0.24
    å¸IJ
    -0.23
    POSITIVE LOGITS
    æĸĩåѦ
    0.28
    æѧè§Ĩ
    0.26
    /front
    0.26
    ç®į
    0.25
     Yas
    0.25
    å¼ĥ
    0.24
    ytt
    0.24
     reinforcements
    0.23
    IClient
    0.23
    æĥij
    0.23
    Activations Density 37.487%

    No Known Activations