© 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. 88810
    Prev
    Next
    INDEX
    Explanations

    answering questions

    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
    åīįæıIJ
    -0.30
    æķ£
    -0.28
    ика
    -0.28
    mid
    -0.27
    icare
    -0.27
     effort
    -0.26
    alias
    -0.26
    çļĦåīįæıIJ
    -0.26
     Weg
    -0.25
    ç£Ĭ
    -0.25
    POSITIVE LOGITS
    heits
    0.27
    -stream
    0.26
    寤
    0.25
     Naughty
    0.25
    —↵↵
    0.24
     Hubb
    0.24
    ä¸ĩæĪ·
    0.24
    >Show
    0.23
     LANGUAGE
    0.23
     Fault
    0.23
    Activations Density 29.992%

    No Known Activations