© 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. 33-TRANSCODER-HP
    7. 52576
    Prev
    Next
    INDEX
    Explanations

    military/political conflict

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĺ²å¾¡
    -0.31
    éĺ²åį«
    -0.30
    éĺ²æĬ¤
    -0.29
     defenses
    -0.29
     defensive
    -0.28
     Shield
    -0.28
     shields
    -0.27
    ëĦĪ
    -0.27
     Defender
    -0.27
     protected
    -0.26
    POSITIVE LOGITS
     posted
    0.27
    Exist
    0.27
    缴éĢļ车
    0.26
    ĮĢ
    0.25
     minist
    0.25
    é¾Ħ
    0.24
     posts
    0.24
    illery
    0.24
     dent
    0.24
    getPost
    0.24
    Activations Density 0.016%

    No Known Activations