© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107724
    Prev
    Next
    INDEX
    Explanations

    names

    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
     Emit
    -0.29
     Ratio
    -0.28
    ð
    -0.27
    ¼
    -0.26
    æŁ´
    -0.26
    _RATIO
    -0.25
     sou
    -0.25
    åįĬ天
    -0.25
     emit
    -0.25
    æĹĨ
    -0.25
    POSITIVE LOGITS
     stag
    0.28
    etration
    0.28
    iamond
    0.28
    ephy
    0.26
    orney
    0.25
    天èµĭ
    0.25
    uggy
    0.24
    Alchemy
    0.23
    izons
    0.23
    帮åĬ©ä¼ģä¸ļ
    0.23
    Activations Density 0.991%

    No Known Activations