© 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. 106921
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
     initState
    -0.26
    headed
    -0.26
    éĵģè·¯
    -0.25
    寡
    -0.25
    彩èī²
    -0.25
    åŁİéĻħ
    -0.25
     borough
    -0.25
    older
    -0.24
     citt
    -0.23
    Introduced
    -0.23
    POSITIVE LOGITS
    åĢŁ
    0.32
    ç»ıæµİæįŁå¤±
    0.31
    åĩı
    0.29
     rent
    0.29
    åĢŁè´·
    0.29
    esan
    0.28
    èµĶåģ¿
    0.28
    hum
    0.27
    èŀįèµĦ
    0.27
    çĶŁäº§èĥ½åĬĽ
    0.26
    Activations Density 0.942%

    No Known Activations