© 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. 19-TRANSCODER-HP
    7. 6464
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ĭ天çļĦ
    -0.28
     sleeper
    -0.27
    çĦī
    -0.25
    .DEFINE
    -0.25
    oons
    -0.25
    å¨ĺ
    -0.24
     sealing
    -0.24
    åĶij
    -0.23
    -figure
    -0.23
     Redistribution
    -0.23
    POSITIVE LOGITS
    çķ¥
    0.30
    il
    0.28
     drives
    0.28
    lesh
    0.27
    ilan
    0.27
    ures
    0.26
    æŀľ
    0.25
    åħ¥æīĭ
    0.25
    orth
    0.25
    Levels
    0.25
    Activations Density 0.017%

    No Known Activations