© 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. 29674
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    å¸ĤæķĻèĤ²
    -0.27
     focus
    -0.25
    æ³ī
    -0.24
     Osw
    -0.24
    focus
    -0.23
     ciÄħ
    -0.23
    ombo
    -0.23
     Wes
    -0.23
    uste
    -0.23
    ptic
    -0.23
    POSITIVE LOGITS
    dyn
    0.30
    Dyn
    0.26
    istan
    0.25
     oppos
    0.25
    è¦ģåİ»
    0.25
     opposed
    0.24
    ditor
    0.24
     dyn
    0.24
    langs
    0.24
    åĵī
    0.24
    Activations Density 5.529%

    No Known Activations