© 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. 162909
    Prev
    Next
    INDEX
    Explanations

    code templates

    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
     Cla
    -0.26
    âİŁ
    -0.26
    Isl
    -0.24
    \Page
    -0.24
    erti
    -0.24
    ByExample
    -0.24
    æľīçĶ¨çļĦ
    -0.24
    ouncements
    -0.24
    getObject
    -0.24
     beneficial
    -0.24
    POSITIVE LOGITS
    æĮĸ
    0.30
    èģĶç³»
    0.28
    reopen
    0.27
     Tor
    0.27
     bÄĥng
    0.26
    æµģåĬ¨æĢ§
    0.25
     contacts
    0.24
     astronom
    0.24
    å¾Ī
    0.24
    éĩĩ
    0.23
    Activations Density 0.002%

    No Known Activations