© 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
    2. Qwen3-4B
    3. 35-TRANSCODER-HP
    4. 40002
    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_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hydro
    -0.39
    theless
    -0.31
    hydro
    -0.30
    åľ¨è¿Ļ个
    -0.29
    entication
    -0.28
    ydro
    -0.26
     overcrow
    -0.24
    oretical
    -0.24
     convo
    -0.24
     challeng
    -0.24
    POSITIVE LOGITS
    ration
    0.30
    Cos
    0.29
     Fauc
    0.29
     Nation
    0.29
     Cups
    0.29
     Cup
    0.28
     Honey
    0.28
     Parts
    0.28
     Labs
    0.28
    xy
    0.28
    Activations Density 0.128%

    No Known Activations