© 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. 56958
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    .si
    -0.25
     virt
    -0.25
    eli
    -0.25
     ferment
    -0.25
     jun
    -0.24
     equals
    -0.24
    移åĪ°
    -0.24
    åľ¨çİ°åľº
    -0.24
     sit
    -0.24
    éĴĪ
    -0.23
    POSITIVE LOGITS
    çĮ©
    0.31
    åĩºåĵģ
    0.29
    comings
    0.28
    åĽ½åľŁ
    0.27
    éŃĦ
    0.27
    åľ°ä¸Ń
    0.27
    æ¡£
    0.27
    çĤ¹å¤´
    0.26
    å¿ĥåĬ¨
    0.26
    èħ¿
    0.26
    Activations Density 0.001%

    No Known Activations