© 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. 43869
    Prev
    Next
    INDEX
    Explanations

    animals and conservation

    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
    èŀŃ
    -0.28
    Æ°á»Ľi
    -0.27
    chw
    -0.27
    %B
    -0.27
     khảo
    -0.26
     Campos
    -0.26
    erne
    -0.26
     park
    -0.26
    çĶ°
    -0.26
    åł°
    -0.26
    POSITIVE LOGITS
    ä¸Ńå¼ı
    0.30
    ä¿®çIJĨ
    0.27
    agnar
    0.27
    婺
    0.26
    Ranges
    0.26
    çĭĢ
    0.26
    æĹłè¾ľ
    0.26
     Patriot
    0.26
     rel
    0.26
    æİ¥åĬĽ
    0.25
    Activations Density 0.001%

    No Known Activations