© 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. 23504
    Prev
    Next
    INDEX
    Explanations

    Biographies

    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
    HomeController
    -0.36
     HomeController
    -0.30
    ums
    -0.29
    RootElement
    -0.27
    DebugEnabled
    -0.27
    nu
    -0.26
    _LIB
    -0.25
    pollo
    -0.24
    æķ£
    -0.24
    Fu
    -0.23
    POSITIVE LOGITS
    irk
    0.28
    åı£æ°Ķ
    0.27
    åı£æ°´
    0.26
    endors
    0.25
    ersed
    0.25
     sincere
    0.24
    çı©
    0.23
    çļĦæĬĢæľ¯
    0.23
    몰
    0.23
    apult
    0.23
    Activations Density 0.002%

    No Known Activations