© 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. 17827
    Prev
    Next
    INDEX
    Explanations

    academic/technical texts

    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
    好åIJĹ
    -0.29
    å¼ģ
    -0.28
    ä¾
    -0.27
    æľį
    -0.27
    IBE
    -0.27
    owitz
    -0.27
    è¿ĩåĪĨ
    -0.26
    ari
    -0.26
    FILE
    -0.26
    lay
    -0.25
    POSITIVE LOGITS
     realization
    0.31
    è¿ĽåĮĸ
    0.27
     evolve
    0.27
     Observation
    0.27
     evolved
    0.27
     realized
    0.26
     evolutionary
    0.26
    ستاÙĨ
    0.26
     evolution
    0.26
    isc
    0.25
    Activations Density 1.330%

    No Known Activations