© 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. 107852
    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
     Ensemble
    -0.31
    妥
    -0.30
     ensemble
    -0.28
    EMS
    -0.26
     Feder
    -0.24
     mat
    -0.24
    让人们
    -0.24
     Toy
    -0.24
    å®ļçĤ¹
    -0.23
    èĭij
    -0.23
    POSITIVE LOGITS
    bie
    0.27
    ÃŁe
    0.27
    istik
    0.25
    /XML
    0.24
    é¼¾
    0.24
    èªŀ
    0.24
    èĽĽ
    0.23
    глав
    0.23
    oug
    0.23
    ymi
    0.23
    Activations Density 0.837%

    No Known Activations