© 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. 23053
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    oley
    -0.25
    FirstResponder
    -0.25
    æĶ¿åįı
    -0.25
    ners
    -0.25
    ÙħÙĬÙĨ
    -0.25
     TELE
    -0.25
    ForObject
    -0.25
    è¯į
    -0.25
    onomic
    -0.24
    éĶģå®ļ
    -0.24
    POSITIVE LOGITS
    è¯Ŀ说
    0.26
    æ·±å¤ľ
    0.26
    reetings
    0.26
    çĤ·
    0.25
     spirit
    0.25
    irsch
    0.25
     today
    0.25
    Initializing
    0.24
     vit
    0.24
     æĿ
    0.24
    Activations Density 0.010%

    No Known Activations