© 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. 23-TRANSCODER-HP
    7. 162045
    Prev
    Next
    INDEX
    Explanations

    Measurable Properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĿı
    -0.28
    åīįæıIJ
    -0.28
    åĽŃ
    -0.27
    åīį身
    -0.27
    bdb
    -0.26
    _basis
    -0.26
    ustain
    -0.24
    éĻIJãĤĬ
    -0.24
    为æĬĵ
    -0.24
    é¢Ĩ导ä¸ĭ
    -0.23
    POSITIVE LOGITS
     overall
    0.28
     put
    0.25
     tolerated
    0.24
     proposed
    0.24
     required
    0.24
    overall
    0.24
     drops
    0.24
     mismatch
    0.24
     differed
    0.24
    VC
    0.24
    Activations Density 0.039%

    No Known Activations