© 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. 30035
    Prev
    Next
    INDEX
    Explanations

    phi

    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
    elow
    -0.27
     ~(
    -0.27
    åĴĮæľįåĬ¡
    -0.26
    AndUpdate
    -0.25
    Sizer
    -0.24
     contribution
    -0.24
     Contribution
    -0.24
    èĩ§
    -0.24
    isi
    -0.24
    Encoder
    -0.24
    POSITIVE LOGITS
    庵
    0.29
    aris
    0.27
    çļĦ主é¢ĺ
    0.27
    nell
    0.27
    åĢŃ
    0.26
    临æŶ
    0.26
    çİ°å®ŀä¸Ń
    0.26
    -themed
    0.26
    å¥ĩ
    0.25
    åŃĹæł·
    0.25
    Activations Density 1.470%

    No Known Activations