© 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. 52945
    Prev
    Next
    INDEX
    Explanations

    locations and origins

    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
    åİŁåĽłä¹ĭä¸Ģ
    -0.29
    RARY
    -0.27
    -origin
    -0.27
    tml
    -0.26
     facult
    -0.26
    kits
    -0.26
    åİŁåĽł
    -0.25
    å¤©åºľ
    -0.25
    裹
    -0.24
    æĹĦ
    -0.24
    POSITIVE LOGITS
    ìĭ±
    0.26
    Live
    0.26
     n
    0.26
    enge
    0.26
    iren
    0.25
     Live
    0.25
     live
    0.25
     region
    0.25
    Place
    0.25
    rels
    0.25
    Activations Density 0.008%

    No Known Activations