© 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. 43957
    Prev
    Next
    INDEX
    Explanations

    scientific/biological contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -li
    -0.26
     vil
    -0.26
    ç»´å¥ĩ
    -0.26
    hell
    -0.25
    li
    -0.25
    æķij人
    -0.25
    swift
    -0.24
    åį°èĬ±
    -0.24
    æ¢ħèĬ±
    -0.24
    -lib
    -0.23
    POSITIVE LOGITS
    ç»Ħç»ĩ
    0.59
     organic
    0.49
     tissue
    0.48
    æľīæľº
    0.47
    çµĦç¹Ķ
    0.45
     Organic
    0.43
    organic
    0.40
     plant
    0.37
    æłĩ
    0.35
    大æ°Ķ
    0.35
    Activations Density 0.001%

    No Known Activations