© 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. 88897
    Prev
    Next
    INDEX
    Explanations

    story snippets

    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
    )!↵
    -0.29
    åıįèĢĮ
    -0.27
    ãģĵãģĿ
    -0.26
    #error
    -0.25
    çı¥
    -0.24
    esper
    -0.23
    ULL
    -0.23
    .eng
    -0.23
     maks
    -0.23
    yrı
    -0.23
    POSITIVE LOGITS
    bsites
    0.30
    rais
    0.27
    wood
    0.25
    åĺīå¹´
    0.25
    åŁ¹åħ»åѦçĶŁ
    0.25
     appro
    0.24
    GRAM
    0.23
    łģ
    0.23
    enido
    0.23
    åĩ½
    0.23
    Activations Density 7.967%

    No Known Activations