© 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. 29540
    Prev
    Next
    INDEX
    Explanations

    ole

    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
    xis
    -0.28
     Weather
    -0.28
     weather
    -0.28
    ngrx
    -0.27
    Weather
    -0.27
    åŃº
    -0.26
    findFirst
    -0.25
    _lens
    -0.25
    weather
    -0.25
    绺
    -0.24
    POSITIVE LOGITS
     propag
    0.30
    -server
    0.29
    -prop
    0.29
    suit
    0.28
     decor
    0.28
     servers
    0.28
    _server
    0.27
    ä¹ı
    0.27
     meshes
    0.27
     DOM
    0.27
    Activations Density 1.653%

    No Known Activations