© 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. 162745
    Prev
    Next
    INDEX
    Explanations

    Notes

    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
    ainment
    -0.28
    anded
    -0.27
    uvw
    -0.25
    rovers
    -0.25
    emp
    -0.24
    ampil
    -0.24
     colle
    -0.24
     Emp
    -0.24
    lying
    -0.24
     kr
    -0.23
    POSITIVE LOGITS
    çļĦä¸ĢäºĽ
    0.26
    arer
    0.26
    arto
    0.25
     Redistributions
    0.24
    egis
    0.24
    éĢļ讯åijĺ
    0.24
     former
    0.24
    ients
    0.24
    çļĦ人çī©
    0.24
    Licensed
    0.23
    Activations Density 0.013%

    No Known Activations