© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30433
    Prev
    Next
    INDEX
    Explanations

    tiredness and conversational

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Experienced
    -0.27
    ogi
    -0.27
    GRESS
    -0.26
    pered
    -0.26
    è¾Ļ
    -0.25
     experienced
    -0.25
    æķĻç»ĥ
    -0.25
     drinks
    -0.25
    phia
    -0.25
     jerseys
    -0.24
    POSITIVE LOGITS
     expose
    0.26
    å¤ĸè´¸
    0.25
    .openg
    0.25
     Carpet
    0.25
     exposing
    0.24
    翻身
    0.24
    daq
    0.24
     contamination
    0.24
    imator
    0.24
    rens
    0.24
    Activations Density 0.508%

    No Known Activations