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

    Media titles and terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸ¹åľĨ
    -0.30
    徨
    -0.27
    åĵģç§į
    -0.27
    urgeon
    -0.26
    åĬ¨éĿĻ
    -0.26
    oftware
    -0.25
    nect
    -0.25
    éŀħ
    -0.25
    _ARB
    -0.25
     Herman
    -0.24
    POSITIVE LOGITS
    éĺ»åĬĽ
    0.29
     imag
    0.26
    aga
    0.25
     consistent
    0.25
    uw
    0.24
     ready
    0.24
    Past
    0.24
    ystore
    0.24
     fired
    0.24
     wire
    0.24
    Activations Density 0.038%

    No Known Activations