© 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. 63
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     Candidate
    -0.27
    orrent
    -0.27
    (Dense
    -0.26
    abar
    -0.25
     senses
    -0.24
    ypes
    -0.24
    aset
    -0.24
    çĶ±äºİ
    -0.24
    hya
    -0.23
    laus
    -0.23
    POSITIVE LOGITS
    磮
    0.29
     wink
    0.26
    olo
    0.25
    ceb
    0.25
     ↵↵
    0.24
    çĺª
    0.24
     \↵↵
    0.24
     androidx
    0.24
    代è¨Ģ
    0.24
    æľįåĬ¡äºİ
    0.24
    Activations Density 0.123%

    No Known Activations