© 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. 32-TRANSCODER-HP
    7. 43375
    Prev
    Next
    INDEX
    Explanations

    hydro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AttributeName
    -0.29
     sidew
    -0.28
    elman
    -0.27
    æľ¬åľŁ
    -0.27
     reserv
    -0.25
     Span
    -0.24
    ivia
    -0.24
    å¿Ĺ强
    -0.24
    秧
    -0.24
    onia
    -0.24
    POSITIVE LOGITS
    logic
    0.32
    logical
    0.31
    _intr
    0.29
    humidity
    0.28
    æĮģ
    0.28
    environment
    0.28
    æ°´èµĦæºIJ
    0.27
    intr
    0.27
    hydro
    0.26
    ecurity
    0.26
    Activations Density 0.003%

    No Known Activations