© 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. 14-TRANSCODER-HP
    7. 40916
    Prev
    Next
    INDEX
    Explanations

    technical/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼łæŁĵ
    -0.30
    æīĢæľī人
    -0.28
    uzzi
    -0.28
    éĦļ
    -0.27
    ä¸Ģæ³¢
    -0.26
     OnePlus
    -0.26
    prd
    -0.24
    gli
    -0.24
    Vendor
    -0.24
    ä¸įåģľçļĦ
    -0.23
    POSITIVE LOGITS
     bul
    0.28
     programs
    0.28
    0.27
     urg
    0.25
    agra
    0.25
     vertices
    0.25
     end
    0.25
     unpl
    0.25
    ä¸įå®Į
    0.24
     tools
    0.24
    Activations Density 0.852%

    No Known Activations