© 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. 43895
    Prev
    Next
    INDEX
    Explanations

    ex

    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
     Tor
    -0.27
    pired
    -0.27
    å·²ä¹ħçļĦ
    -0.27
    çĥŁçģ«
    -0.27
    å¤ļå¹´çļĦ
    -0.26
    æĹ¥æŃ£å¼ı
    -0.26
    askan
    -0.25
    ãģĽãģ¦
    -0.25
    Tor
    -0.25
     sidel
    -0.25
    POSITIVE LOGITS
    ertil
    0.30
    elize
    0.28
     $($
    0.27
    ce
    0.27
    _MO
    0.27
    cel
    0.26
    eri
    0.26
    笼
    0.26
    zial
    0.25
    çĵ®
    0.25
    Activations Density 0.005%

    No Known Activations