© 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. 89068
    Prev
    Next
    INDEX
    Explanations

    about

    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
    auss
    -0.27
    pot
    -0.25
    uc
    -0.25
    ISS
    -0.25
     Newman
    -0.25
    _FLASH
    -0.25
    æ½ľåľ¨
    -0.25
    æ½ľåĬĽ
    -0.24
    Steam
    -0.24
    ac
    -0.24
    POSITIVE LOGITS
    antro
    0.29
    laden
    0.28
    ascus
    0.27
     generated
    0.26
    çĶŁæĪIJ
    0.26
    kins
    0.26
    èIJ½åIJİ
    0.25
     unsub
    0.25
    æĪijçľĭ
    0.24
     +++
    0.24
    Activations Density 6.837%

    No Known Activations