© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 20-TRANSCODER-HP
    4. 142006
    Prev
    Next
    INDEX
    Explanations

    Beginning of sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eor
    -0.28
    æĮīè§Ħå®ļ
    -0.27
    eto
    -0.27
    phin
    -0.25
    æĹıèĩªæ²»åİ¿
    -0.25
    eya
    -0.24
     prefixed
    -0.24
     Danger
    -0.24
    è¦ģçľĭ
    -0.23
    çļŀ
    -0.23
    POSITIVE LOGITS
    ’t
    0.32
    è¿ĻéĩĮçļĦ
    0.27
    ”
    0.27
    ’s
    0.26
    è¯ĬæīĢ
    0.25
    ↵
    0.24
    ’an
    0.23
    çΏçΏ
    0.23
    ouples
    0.23
    æ¸Ķ
    0.23
    Activations Density 9.023%

    No Known Activations