© 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. 33-TRANSCODER-HP
    7. 54814
    Prev
    Next
    INDEX
    Explanations

    Dist

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸įä¸Ģæł·
    -0.28
     smack
    -0.26
    å¯Ĩå°ģ
    -0.26
    difference
    -0.26
    åij½ä¸Ń
    -0.25
     Amar
    -0.25
     independently
    -0.24
     independence
    -0.24
    _difference
    -0.24
    Difference
    -0.24
    POSITIVE LOGITS
     dist
    1.07
    dist
    0.92
     Dist
    0.90
    -dist
    0.88
    Dist
    0.80
    _dist
    0.79
    (dist
    0.79
    .dist
    0.76
    	dist
    0.73
    /dist
    0.69
    Activations Density 0.252%

    No Known Activations