© 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. 25-TRANSCODER-HP
    7. 107777
    Prev
    Next
    INDEX
    Explanations

    electronic circuits/semiconductors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    throp
    -0.28
     '*.
    -0.28
     Growing
    -0.27
    æ¸ĹéĢı
    -0.25
    累累
    -0.24
    кÑĢаÑģ
    -0.24
    arÃŃa
    -0.24
     "*.
    -0.24
    Å¡ÃŃ
    -0.24
    usted
    -0.24
    POSITIVE LOGITS
    è§Ī
    0.29
    FLT
    0.28
     deficit
    0.28
    åĮ£
    0.26
     LICENSE
    0.26
     completion
    0.26
    éĹ»
    0.25
    åĭ¿
    0.25
     integral
    0.25
    çļĦäºĭå®ŀ
    0.25
    Activations Density 1.002%

    No Known Activations