© 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. 23-TRANSCODER-HP
    7. 24316
    Prev
    Next
    INDEX
    Explanations

    }

    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
    æĿĥ
    -0.30
    èĻļåģĩ
    -0.27
    æ²ī
    -0.27
    被åĬ¨
    -0.26
    èµĦ产éĩįç»Ħ
    -0.26
    ",↵↵
    -0.25
    eka
    -0.25
    idth
    -0.24
     (↵↵
    -0.24
    çīĪæĿĥ声æĺİ
    -0.24
    POSITIVE LOGITS
     home
    0.35
     Home
    0.34
    Home
    0.32
     Field
    0.30
    Toggle
    0.28
    æ»´
    0.28
    /Home
    0.28
    ãĥĽãĥ¼ãĥł
    0.27
     whit
    0.27
    .Home
    0.26
    Activations Density 0.036%

    No Known Activations