© 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. 53658
    Prev
    Next
    INDEX
    Explanations

    say the ending -ography

    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
    uled
    -0.28
    纤
    -0.26
    FFE
    -0.26
    Fizz
    -0.26
    ertools
    -0.26
    robots
    -0.25
    nas
    -0.24
     éc
    -0.24
    imonials
    -0.24
    tweets
    -0.24
    POSITIVE LOGITS
     graph
    1.09
    graph
    1.05
     graphs
    0.93
    -graph
    0.93
     Graph
    0.92
    GRAPH
    0.91
    Graph
    0.91
    _graph
    0.86
    åĽ¾å½¢
    0.86
    	graph
    0.85
    Activations Density 0.025%

    No Known Activations