© 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. 109453
    Prev
    Next
    INDEX
    Explanations

    savings

    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
    lian
    -0.28
    onder
    -0.27
    ltre
    -0.25
     Ratio
    -0.25
     Relation
    -0.25
    гоÑĤов
    -0.25
    æīĭä¸ĭ
    -0.25
    OND
    -0.24
    aday
    -0.24
     LF
    -0.23
    POSITIVE LOGITS
    _DA
    0.26
    ogy
    0.26
     modeled
    0.26
    ä¸Ģè§Ī
    0.25
     disadvantage
    0.25
    æijĺè¦ģ
    0.24
    ä¸Ģèĩ´
    0.24
     headline
    0.24
     statewide
    0.24
    iest
    0.23
    Activations Density 0.022%

    No Known Activations