© 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. 35-TRANSCODER-HP
    7. 39702
    Prev
    Next
    INDEX
    Explanations

    Technical/Academic writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é£İåIJ¹
    -0.27
    åģļä¸įåĪ°
    -0.24
     bezpoÅĽ
    -0.23
     najczÄĻÅĽciej
    -0.23
    å¿ĥæĥ³
    -0.23
    éĽĨåĽ¢èĤ¡ä»½
    -0.23
     yapılacak
    -0.23
     screwed
    -0.23
     disappoint
    -0.22
    è¿Ļ个ä¸ĸçķĮ
    -0.22
    POSITIVE LOGITS
     ar
    0.55
     r
    0.53
     l
    0.51
     ur
    0.51
     ld
    0.50
     er
    0.50
     rn
    0.50
     rs
    0.50
     ng
    0.50
     ir
    0.50
    Activations Density 97.088%

    No Known Activations