© 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. 109214
    Prev
    Next
    INDEX
    Explanations

    commit

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Escorts
    -0.29
    æĬķåħ¥
    -0.28
    ä»»åij½
    -0.27
    dee
    -0.27
    ỡ
    -0.27
    -banner
    -0.26
    ouri
    -0.25
    çī¹éĤĢ
    -0.25
     allocation
    -0.24
     fleets
    -0.24
    POSITIVE LOGITS
    ена
    0.27
    ูà¹Ī
    0.26
     stopping
    0.26
    èIJ¥ä¸ļ
    0.26
    igg
    0.25
    çĩŁ
    0.25
    ToDevice
    0.25
    åĽŀ头
    0.24
    ull
    0.24
    ingen
    0.24
    Activations Density 0.126%

    No Known Activations