© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41397
    Prev
    Next
    INDEX
    Explanations

    environmental

    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
    orde
    -0.33
    åīįæīĢæľªæľī
    -0.28
    è´£ç¼ĸ
    -0.28
     shave
    -0.28
    åį¤
    -0.27
    çŃĶé¢ĺ
    -0.27
     sheets
    -0.25
     nghiá»ĩp
    -0.24
    äm
    -0.24
    amate
    -0.24
    POSITIVE LOGITS
     environmental
    0.31
    ä¸Ģç«Ļ
    0.31
     Environmental
    0.30
    Environmental
    0.30
     env
    0.28
    eron
    0.27
    environment
    0.27
    	env
    0.27
    çݯä¿Ŀ
    0.26
     ENV
    0.26
    Activations Density 0.005%

    No Known Activations