© 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. 161788
    Prev
    Next
    INDEX
    Explanations

    technical questions

    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
    ICATION
    -0.26
    èĦ
    -0.25
    озвÑĢаÑī
    -0.25
    æĭį
    -0.25
    emente
    -0.24
    arter
    -0.24
    -Identifier
    -0.24
    åģıåģı
    -0.24
    åıĮæīĭ
    -0.23
    FromArray
    -0.23
    POSITIVE LOGITS
    (expected
    0.28
     expected
    0.28
    çIJĨ论ä¸Ĭ
    0.28
     equations
    0.28
    _expected
    0.27
     expectations
    0.26
    expected
    0.26
    .expected
    0.26
     Revel
    0.26
    é¢ĦæľŁ
    0.25
    Activations Density 0.004%

    No Known Activations