© 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. 56808
    Prev
    Next
    INDEX
    Explanations

    Requirement, must

    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
     guaranteed
    -0.43
     guarantee
    -0.43
    ä¿Ŀéļľ
    -0.39
    ä¿Ŀè¯ģ
    -0.37
     warranty
    -0.35
    ä¿Ŀä¿®
    -0.34
     guarantees
    -0.34
     promise
    -0.34
     warranties
    -0.33
     Guarantee
    -0.33
    POSITIVE LOGITS
    å¿ħé¡»
    0.63
     must
    0.63
    must
    0.59
     Must
    0.58
    Must
    0.55
    å¿ħéłĪ
    0.55
     requirements
    0.52
    é¡»
    0.50
    .must
    0.49
     Requirements
    0.48
    Activations Density 0.003%

    No Known Activations