© 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. 27-TRANSCODER-HP
    7. 56902
    Prev
    Next
    INDEX
    Explanations

    Ger

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extrav
    -0.28
    çħ§
    -0.27
    ignon
    -0.25
    åĶĩ
    -0.24
    IBUTE
    -0.24
    PIC
    -0.24
    溺
    -0.24
    ä»»ä½ķæŶåĢĻ
    -0.24
    ÑĢаниÑĨ
    -0.24
    enschaft
    -0.23
    POSITIVE LOGITS
    åĸĩ
    0.28
    jets
    0.28
    åľ¨åIJĮä¸Ģ
    0.27
    ä¼ı
    0.26
    å®Ļ
    0.25
     Mercy
    0.25
     achter
    0.24
    æ·ŀ
    0.24
    bolt
    0.24
    less
    0.23
    Activations Density 0.031%

    No Known Activations