© 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. 12-TRANSCODER-HP
    7. 22962
    Prev
    Next
    INDEX
    Explanations

    Conform/Comply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    curities
    -0.32
    eries
    -0.32
    istrate
    -0.26
    stry
    -0.26
    smith
    -0.25
    glomer
    -0.25
    åIJĪä½ľåħ³ç³»
    -0.25
    ä»·åĢ¼éĵ¾
    -0.25
     Spect
    -0.24
    ath
    -0.24
    POSITIVE LOGITS
    æĸĻ
    0.30
    ä¸ĩä¸Ģ
    0.28
     elect
    0.28
    sei
    0.25
    æīįç®Ĺ
    0.25
     nodes
    0.24
    Òij
    0.24
    iad
    0.24
    esa
    0.24
    æ´Ĵ
    0.23
    Activations Density 0.023%

    No Known Activations