© 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. 57960
    Prev
    Next
    INDEX
    Explanations

    end

    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
     rake
    -0.26
     Maurit
    -0.25
    é¦ĸå¸Ń
    -0.25
    uce
    -0.25
    顼
    -0.24
     Dummy
    -0.24
     Constants
    -0.24
     Pompe
    -0.24
    ÙĤاء
    -0.24
     Pers
    -0.24
    POSITIVE LOGITS
     inner
    0.61
     nested
    0.58
     outer
    0.57
     loop
    0.52
    Outer
    0.51
    nested
    0.50
     loops
    0.50
    (inner
    0.49
     Outer
    0.48
    loop
    0.47
    Activations Density 0.001%

    No Known Activations