© 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. 89860
    Prev
    Next
    INDEX
    Explanations

    Speculation/Possibility

    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
    为ä½ķ
    -0.30
    为ä»Ģä¹Ī
    -0.30
     why
    -0.28
    why
    -0.26
    ä¸įæľį
    -0.26
    rac
    -0.26
    第äºĮ次
    -0.26
    为åķ¥
    -0.25
    atsapp
    -0.25
    kehr
    -0.25
    POSITIVE LOGITS
    Formats
    0.27
    UGH
    0.27
    头åıij
    0.25
    身边
    0.25
    åľºåIJĪ
    0.25
    .UUID
    0.25
    éªļ
    0.25
    ë§ī
    0.24
    æĪĸå°Ĩ
    0.24
     scenes
    0.24
    Activations Density 8.785%

    No Known Activations