© 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. 9-TRANSCODER-HP
    7. 29538
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hift
    -0.26
    getElement
    -0.25
    ç°ĩ
    -0.25
    awn
    -0.25
    å°Ĭéĩį
    -0.25
     connected
    -0.24
     µ
    -0.24
     stout
    -0.24
     associated
    -0.23
    æijĦå½±
    -0.23
    POSITIVE LOGITS
    /sdk
    0.30
    itories
    0.26
    æµ·è¾¹
    0.25
     SMP
    0.24
    æµ·åŁŁ
    0.24
     TValue
    0.24
    olia
    0.24
    ltk
    0.24
    setItem
    0.24
    toolbox
    0.23
    Activations Density 27.085%

    No Known Activations