© 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. 107550
    Prev
    Next
    INDEX
    Explanations

    cereal or serializer

    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
    adol
    -0.31
     interesse
    -0.26
     LinkedIn
    -0.26
    HN
    -0.26
    edo
    -0.26
    located
    -0.25
    .BigInteger
    -0.25
    å¾¼
    -0.24
     Slam
    -0.24
    ERING
    -0.23
    POSITIVE LOGITS
    èµ·åºĬ
    0.27
    åī¯
    0.26
    pies
    0.26
    æĭ¿åĩº
    0.26
    ifs
    0.26
     stick
    0.26
    å«Įçĸij
    0.25
    æŁľåı°
    0.25
     rep
    0.25
    sheets
    0.25
    Activations Density 0.953%

    No Known Activations