© 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. 33-TRANSCODER-HP
    7. 53936
    Prev
    Next
    INDEX
    Explanations

    scientific, code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enus
    -0.27
    宣
    -0.27
    åĶĩ
    -0.26
    irus
    -0.25
    ariate
    -0.25
    enheim
    -0.25
    ãĥĭãĤ¢
    -0.24
    icolor
    -0.24
    ouser
    -0.24
    /moment
    -0.24
    POSITIVE LOGITS
     rest
    0.29
    (er
    0.27
    ÑģÑĤвенно
    0.26
    .Automation
    0.26
    äºĨä¸Ģæī¹
    0.24
    åIJ¸åıĸ
    0.24
     sore
    0.24
    ero
    0.24
    èĦĪ
    0.24
     sub
    0.24
    Activations Density 0.004%

    No Known Activations