© 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. 31-TRANSCODER-HP
    7. 19897
    Prev
    Next
    INDEX
    Explanations

    conf word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĮºåĪĨ
    -0.29
     distinguish
    -0.28
    åĮºåĪ«
    -0.27
    otland
    -0.25
     incorrect
    -0.25
    ael
    -0.24
    æīĵçĮİ
    -0.24
     erroneous
    -0.24
    neys
    -0.23
     OSError
    -0.23
    POSITIVE LOGITS
     conf
    1.61
     Conf
    1.50
    conf
    1.48
    Conf
    1.41
    -conf
    1.31
    _conf
    1.25
     CONF
    1.24
    (conf
    1.23
    	conf
    1.21
    .conf
    1.19
    Activations Density 9.504%

    No Known Activations