© 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. 89486
    Prev
    Next
    INDEX
    Explanations

    a/an

    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
    arez
    -0.29
    ^K
    -0.27
     Demp
    -0.26
    иÑĢовки
    -0.26
     Damien
    -0.25
    åIJİæİĴ
    -0.25
     james
    -0.24
     Associates
    -0.24
    èİĵ
    -0.24
    dest
    -0.24
    POSITIVE LOGITS
    iesen
    0.28
    building
    0.28
    èģª
    0.28
    夸
    0.28
    -building
    0.26
    ани
    0.26
    lear
    0.25
    é£İæł¼
    0.25
    åIJ¬è¯´
    0.25
     building
    0.25
    Activations Density 15.405%

    No Known Activations