© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 217
    Prev
    Next
    INDEX
    Explanations

    Greek language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sters
    -0.30
    achel
    -0.27
    EXIT
    -0.26
    (indices
    -0.26
    implements
    -0.25
    ertest
    -0.25
    åĤ¬
    -0.23
    ä¸įçĶ¨
    -0.23
    stairs
    -0.23
     sorry
    -0.23
    POSITIVE LOGITS
    åĽłç´ł
    0.27
    aud
    0.26
    èĩªå¦Ĥ
    0.25
    çļĦåĽłç´ł
    0.24
    gable
    0.24
    minate
    0.24
     factor
    0.24
    inherit
    0.24
    å±ķ示äºĨ
    0.24
    é²ł
    0.24
    Activations Density 0.028%

    No Known Activations