© 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. 32-TRANSCODER-HP
    7. 44170
    Prev
    Next
    INDEX
    Explanations

    liquid measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    dÃŃ
    -0.28
    cold
    -0.28
    èĬĤ
    -0.27
    Cold
    -0.26
     Slow
    -0.26
    æĭĴä¸į
    -0.25
    Ắ
    -0.24
     Cold
    -0.24
    marshall
    -0.24
    cÃŃ
    -0.24
    POSITIVE LOGITS
    itere
    0.31
    å¬
    0.27
    oufl
    0.27
    itudes
    0.26
    iter
    0.26
    athed
    0.25
    numer
    0.25
    opher
    0.25
    ith
    0.25
    iterals
    0.25
    Activations Density 0.001%

    No Known Activations