© 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. 25-TRANSCODER-HP
    7. 109480
    Prev
    Next
    INDEX
    Explanations

    political conflict/geography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     fold
    -0.29
    Fed
    -0.27
     hud
    -0.27
    fps
    -0.25
    Inf
    -0.25
     fps
    -0.24
     Missouri
    -0.24
    fold
    -0.24
    feb
    -0.24
    -fold
    -0.23
    POSITIVE LOGITS
    ResponseStatus
    0.31
    åĨįè§ģ
    0.30
    å»īä»·
    0.28
    éŃĶ鬼
    0.25
    ¨
    0.25
    ç»ĵæŀľæĺ¾ç¤º
    0.25
    头åıij
    0.25
    åºĵéĩĮ
    0.24
    Associ
    0.24
    associ
    0.23
    Activations Density 0.034%

    No Known Activations