© 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. 33-TRANSCODER-HP
    7. 53100
    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_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     property
    -0.77
    å±ŀæĢ§
    -0.75
     properties
    -0.72
     Property
    -0.67
     attributes
    -0.66
     getProperty
    -0.65
     attribute
    -0.62
    property
    -0.61
     PROPERTY
    -0.60
     Properties
    -0.60
    POSITIVE LOGITS
    apia
    0.28
    å¼¹
    0.27
    po
    0.27
    .notifyDataSetChanged
    0.26
    op
    0.25
    çĶµè§Ĩ
    0.24
    å®Įæķ´
    0.24
    pres
    0.24
    TY
    0.24
    ps
    0.24
    Activations Density 0.020%

    No Known Activations